Photometric Supervision

In autonomous driving, perception models often struggle to generalize to new environments due to domain shifts. While unsupervised model adaptation offers a feasible solution without labor-intensive manual labeling, existing methods that rely solely on the ego-vehicle's data often lead to inferior pseudo-labeling performance. To address this critical issue, we propose LDE, Learning from Distributed ``Eyes", a novel framework that transforms collaborative perception (CP) into a source of high-quality supervision for model adaptation. This pseudo-labeling approach is hyperparameter-insensitive and relatively reliable, assuming CP often outperforms single-agent's perception. However, naively implementing this approach encounters (1) the communication bottleneck of sharing rich features under time and bandwidth constraints, (2) the view discrepancy between the CP view and the learner's Field of View (FoV), and (3) the unreliability even in CP-generated labels. To address these issues, we design an adaptation-oriented feature sharing mechanism that selectively transmits the most critical information for adaptation, an FoV filtering method that meticulously eliminates mismatched labels, and a curriculum learning strategy to progressively exploit pseudo labels. Extensive experiments on 3D object detection tasks demonstrate that LDE consistently outperforms both the pre-trained models and state-of-the-art unsupervised adaptation methods.

Self-supervised learning (SSL) can reduce the need for labelled medical images, but the choice of pretext objective remains unclear for lung ultrasound (LUS). Contrastive learning, masked reconstruction, and joint-embedding predictive architectures (JEPA) differ in the space in which their targets are defined, yet existing ultrasound studies compare them under different corpora, backbones, and evaluation protocols. We compare these three objective families using the same encoder backbone, pretraining corpus, optimisation schedule, and frozen-evaluation protocol. Encoders are pretrained on COVID-BLUeS LUS videos and evaluated with linear, $k$NN, and attentive probes at 5%, 10%, 50%, and 100% label budgets. Evaluation is performed on POCUS using patient-level five-fold cross-validation and on the independently acquired Mendeley-Uganda dataset, which is excluded from both pretraining and probe fitting. At the full label budget under linear probing, VideoMAE and V-JEPA achieve $66.5 \pm 13.1$ and $65.4 \pm 11.7$ balanced accuracy on POCUS, while MoCo achieves $42.1 \pm 1.2$. On Mendeley-Uganda, the ranking reverses: MoCo performs best at $62.7 \pm 1.0$, followed by VideoMAE at $53.8 \pm 2.8$, while V-JEPA falls near chance at $35.1 \pm 4.9$. These results show that POCUS probe accuracy alone does not identify the objective that transfers best across datasets. We also outline planned representation-level analyses to examine this reversal. Code is publicly available at https://github.com/moeinheidari7829/LUSVideoSSL.

Multi subject video editing modifies designated subjects while preserving non target content, but faces cross subject attribute leakage, and occlusion ambiguity. Existing approaches rely on masks and struggle to distinguish overlapping subjects or ensure consistent generation. To address these limitations, we propose MDN-Control, a training free framework jointly controlling target localization, occlusion geometry, and appearance initialization. Specifically, mask-guided localization provides consistent target localization, while depth-aware occlusion control resolves ambiguous boundaries between overlapping subjects. We further introduce noise latent prompting, which retrieves Gaussian initializations from a noise library for prompt relevant priors. Experiments on MSVBench show that MDN-Control achieves the lowest CM-Err and the highest Q-Edit, while maintaining competitive text alignment and temporal consistency, demonstrating the effectiveness of combining spatial, geometric, and latent priors for multi subject video editing.

Because dense frame-level annotation of colonoscopy videos is costly, we propose WSPolypNet, a weakly supervised framework for polyp localization using only video-level labels. WSPolypNet employs a 3D convolutional neural network trained with video-level supervision to generate class activation maps (CAMs), which identify candidate polyp regions without requiring frame-level spatial annotations. The CAM-derived localization cues are further enhanced using a multi-view strategy and provided to MedSAM2 as point prompts. MedSAM2 then propagates segmentation masks across the video, refining the coarse localization cues according to polyp boundaries. WSPolypNet achieved CorLoc scores of 47.80%, 43.68%, and 35.01% at IoU thresholds of 0.3, 0.5, and 0.7, respectively, compared with 36.87%, 33.72%, and 27.94% in the single-view setting. For small polyps, the multi-view strategy improved CorLoc@0.5 from 16.01% to 30.97%. The framework also achieved a recall of 94.51%. These results demonstrate the potential of weakly supervised spatiotemporal learning to substantially reduce spatial annotation requirements for polyp localization in colonoscopy videos.

Weakly supervised 3D occupancy prediction reduces the reliance on costly 3D annotations by learning from 2D pseudo-labels generated by vision foundation models. However, existing methods typically use these imperfect pseudo-labels directly as supervision, making occupancy learning vulnerable to erroneous geometric and semantic targets. We observe that agreement across repeated observations provides an inexpensive and reliable cue for assessing pseudo-label reliability. Based on this observation, we propose \textbf{LetOccVote}, a weakly supervised Gaussian-based occupancy framework that leverages cross-frame voting to improve both geometric and semantic supervision. For geometry, Depth Vote exploits cross-frame geometric agreement to refine supported pseudo depth and reject contradictory estimates before volumetric lifting and depth supervision. For semantics, Semantic Vote aggregates pseudo-semantic observations in a shared 3D space to identify reliable and contested evidence, strengthening reliable semantic supervision while filtering unreliable pseudo-label segments. The entire framework is trained solely with 2D pseudo-label supervision without requiring 3D occupancy annotations. On Occ3D-nuScenes, LetOccVote achieves 53.27 IoU and 20.39 mIoU, establishing state-of-the-art performance among methods with 2D pseudo-label supervision.

World models (WMs) have demonstrated strong potential for end-to-end autonomous driving by learning predictive representations of future scene dynamics. However, generating future videos during inference introduces substantial computational overhead, leading many recent driving WMs to adopt a single front camera as input for efficient deployment. This design restricts spatial coverage in safety-critical maneuvers such as lane changes, merges, and turns. To address this limitation, we propose SV-WAM, a surround-view world-action model (WAM) that preserves full six-camera observations while maintaining efficient inference. SV-WAM leverages future-video prediction as dense training supervision for action learning within a shared generative model, rather than as an inference-time output. At the core of this design is an action-centered causal mask that prevents action tokens from attending to future-video tokens during joint action-video denoising. Consequently, the video branch can be discarded at deployment, enabling efficient action-only planning. Furthermore, we introduce a differentiable drivable-area compliance regularizer that penalizes vehicle-footprint corners approaching or crossing drivable boundaries, improving planning safety and boundary awareness. Extensive experiments on the closed-loop NAVSIMv2 benchmark and the open-loop nuScenes benchmark demonstrate that SV-WAM achieves state-of-the-art planning performance with low inference latency and competitive zero-shot transfer capability.

This position paper argues that the absence of labels does not imply the absence of human supervision in visual learning, and urges the research community to identify sources of supervision more explicitly. Many recent methods in computer vision build upon representations learned from large-scale unlabeled data, and are therefore grouped under the same umbrella term unsupervised.'' However, different data curation schemes and training objectives embed substantially different human priors on which models rely, and we argue that one unsupervised'' umbrella term is no longer capturing these distinctions. This ambiguity makes it harder to compare unsupervised learning research conducted under different assumptions, coinciding with a sharp decline in papers titled with ``unsupervised'' in flagship computer vision conferences since 2021, despite continued growth of the field. While we fully embrace pre-training as a strong foundation for modern computer vision, we advocate for a community-level effort toward greater conceptual clarity: authors are encouraged to disclose priors in data selection and learning objectives, and to specify which components of a learning pipeline depend on which assumptions. Standardized disclosure practices can improve academic communication, ensure fairer comparisons, and preserve methodological diversity in unsupervised learning.

Shadow removal is an important preprocessing step for many vision tasks, yet existing supervised methods require paired shadow and shadow-free images, while unsupervised approaches often still rely on shadow masks or shadow-free references. We propose ShadowCLR, an unsupervised framework that learns shadow removal directly from shadow images. Our key observation is that shadows vary across observations while the underlying scene content remains largely consistent. We therefore use consistency across shadow observations as regularization, encouraging the model to recover scene-consistent appearance while suppressing shadow-specific variations. Global and local consistency further enable us to explore visually related images, learn from imperfectly aligned observations, and focus the representation on shared scene information. Experiments on multiple benchmarks show that ShadowCLR achieves competitive and often superior performance over state-of-the-art unsupervised methods, demonstrating that consistency can provide regularization for shadow removal without shadow masks or shadow-free images.

Point cloud video representation learning is crucial for 3D dynamic scene understanding. In this paper, we propose MoSaiC, a novel Motion-Saliency Complementary masked modeling framework for self-supervised point cloud video representation learning. MoSaiC couples three components: Curriculum Motion-Saliency Masking (CMSM), which guides the masking process toward motion-salient tokens under a curriculum schedule; Normal-Flow Motion (NFM) modeling, which supervises the local rigid rotation of each token in the Lie algebra so(3) as an explicit geometric motion target; and Cross-view Token Consistency Prediction (CTCP), which enforces consistency between two complementary masked views at the token level. Together, these components allow MoSaiC to effectively capture both appearance and motion dynamics. Extensive experiments on multiple downstream tasks, including action recognition, temporal action segmentation, and point-level semantic segmentation, demonstrate the effectiveness of our approach.

Monocular depth estimation has achieved strong open-domain generalization, yet reliable robotic deployment remains difficult in transparent, reflective, and specular environments, where depth sensors often produce missing or biased depth. Existing methods often handle such optical failures with scene-specific preprocessing, auxiliary modules, or post-hoc fine-tuning. While effective in constrained settings, these designs increase architectural redundancy and can over-specialize general geometry models to narrow optical scenarios. We revisit this problem as a localized failure mode within base-model training and identify sensor-induced supervision bias as a key bottleneck: models inherit sensor failure patterns from biased real-depth supervision in optically challenging regions. We then introduce OptiGeo, a bias-aware training framework that rehabilitates biased real supervision using a clean-geometry teacher and residual-trimmed alignment. We redefine transparency-targeted rendering as a compact source of clean optical geometry, rather than a large domain-specific fine-tuning set. With only a small targeted rendering set, OptiGeo learns the geometric structure of transparent objects and regions, correcting local geometry distortions that real sensors cannot reliably supervise. Despite only 30M parameters, OptiGeo outperforms substantially larger 300M-scale monocular models and billion-scale multi-view baselines on transparent-scene benchmarks, while remaining competitive on general zero-shot depth and boundary sharpness. Real-world navigation cases further validate its practicality as an efficient perception module in optically challenging scenes.

In vision-based behavior cloning (BC), conventional image augmentations such as Random Crop and Color Jitter often fall short under substantial visual domain shifts, including changes in shadows, distractors, and backgrounds. Superimposition-based augmentations, which blend in-domain and out-of-domain images, have shown promise for improving generalization in computer vision, but their suitability for BC remains uncertain because task-critical semantics, spatiotemporal relationships, and agent-target interactions must be preserved. To address this, we introduce RoboSaGA, a Saliency-Guided Augmentation method within the superimposition family tailored for vision-based BC. RoboSaGA dynamically adjusts augmentation intensity at the pixel level using policy-driven saliency, enabling aggressive augmentation in task-irrelevant regions while preserving task-critical information. It integrates seamlessly into existing architectures without requiring structural modifications or additional learning objectives. Experiments in both simulated and real-world settings show that RoboSaGA preserves in-domain performance while substantially improving robustness to visual domain shifts, including distractor and background changes, as well as lighting and shadow variations. Code is available at https://github.com/Zheyu-Zhuang/RoboSaGA.

Labeled images of small objects hidden in vegetation are scarce, and detectors trained on them generalize poorly across sites. Rather than reusing labels collected at another site, we synthesize labeled training images from a handful of unlabeled photographs of the deployment site itself. A vision--language model generates a coarse 3D vegetation scene from one photograph; placing 3D object meshes in the scene yields bounding boxes, segmentation masks, and per-instance occlusion directly from the scene geometry, without manual annotation. A lightweight adapter fine-tuned on the photographs conditions a diffusion pass that re-textures the renders, and a graded mask-lock sets how much diffusion may touch the object itself. In our runs this grade was the most influential curation choice: lightly diffusing the object improves minority-class recall over fully protecting its pixels, while unrestricted diffusion dissolves it. Trained on these images, a standard detector matched or exceeded its counterpart trained on a larger labeled dataset of real images from a different site, consistently across seeds on a humanitarian-demining benchmark; the comparison is thus unsupervised site adaptation from a handful of photographs against conventional cross-site label reuse. In our ablations the gains were largely insensitive to the photograph and crop budgets, and in-domain accuracy did not predict cross-site performance.

We argue that learning visual representations without labels requires a training signal jointly complete across three non-overlapping objectives: semantic invariance across augmented views, patch-level spatial prediction, and representational non-degeneracy. We formalize these as the observation, prediction, and regularization principles and prove (i) that combining observation and prediction without regularization admits the constant encoder as a global minimizer under negative-free alignment; (ii) that the two objectives are gradient-complementary and structurally non-conflicting at the encoder output; and (iii) that the momentum encoder converges to the same fixed point as the online encoder and provides no collapse guarantee at convergence. Contrastive alignment provides only self-limiting collapse resistance, formalized via an explicit gradient-decay argument. Dropping prediction withholds the spatial training signal by construction; dropping observation forfeits cross-view semantic invariance by construction; at the scale we study, no pair substitutes for the third. Every major self-supervised method is a special case of a single unified energy decomposition. We pair every theoretical claim with a controlled experiment, including a patch-retrieval evaluation for the spatial consequence of prediction.

Vision-language-action (VLA) policies fine-tuned from a fixed scene camera can fail when the camera is moved, even when the task, objects, language, and robot state are unchanged. We study scene-camera viewpoint robustness using only a scene RGB image, language, and proprioception, without camera labels, extrinsics, depth, or point-cloud inputs. The wrist stream is masked throughout to prevent an unperturbed visual shortcut from confounding attribution to scene-camera variation. For flow-based VLAs, we propose to regularize the action-flow velocity field, the quantity directly integrated to generate continuous action chunks. We construct action-equivalent view pairs by resetting original LIBERO demonstrations to the same MuJoCo state and rendering nominal and perturbed scene-camera views. Both views are supervised by flow matching, while a cross-view loss encourages their predicted action-flow velocities to agree at the same sampled flow coordinates. On the LIBERO-Plus camera-perturbation track, our method reaches 87.2$\pm$0.4% (4,797 rollouts per seed across 3 training seeds), +7.4pp over flow-matching-only training on the same paired data (79.8$\pm$0.8%, also 3 seeds) and +12.5pp over naive mixed-camera SFT, while maintaining nominal-camera ID performance (95.0$\pm$0.8%; same-data FM-only: 95.0$\pm$4.3%). A shuffled-pair control collapses to 25.8%, showing that the gain depends on action-equivalent pairing. On a real robot, we evaluate three tabletop tasks with 10 rollouts per task and camera placement; held-out-camera success improves from 53.3% to 74.4% under the same single-scene-RGB inference interface.

Optimal transport (OT) has emerged as an effective framework for unsupervised action segmentation. Yet, in existing OT-based methods, the latent action prototypes that define the OT costs are not re-estimated from the refined frame geometry. Instead, they evolve solely through gradients from the pseudo-label loss. We identify this \emph{representation--prototype inconsistency} as a central bottleneck, particularly around ambiguous transitions and for short or infrequent actions. To address this issue, we build on the recently introduced CLOT, which refines frame embeddings based on estimated segment embeddings, and further re-estimates the action prototypes from the refined frame embeddings. Specifically, we introduce a graph-constrained module that regularizes the OT-refined frame and segment representations by preserving the local neighborhood geometry of the encoder output. An action-embedding refinement step then periodically re-anchors the prototypes to this stabilized representation geometry. We study two instantiations that share the same backbone, graph module, and objective: D-CLOT updates the prototypes using $k$-means, whereas D-CLOT$_{B}$ updates them as OT barycenters weighted by the refined transport plan, yielding an assignment-aware prototype update consistent with the current transport geometry. Across five established benchmarks, both variants improve segment-level quality over CLOT, with per-video gains of up to $+12.7$ F1 and $+10.2$ mIoU (YTI) and activity-level gains of up to $+8.9$ F1 (FS-Eval). We further establish the first unsupervised action-segmentation baseline on Assembly101, a procedural and substantially more fine-grained benchmark than those commonly used in prior work. Extensive ablations and sensitivity analyses demonstrate that the two refinement mechanisms are complementary and robust.

Action labels tell a vision-language-action (VLA) policy which robot commands to imitate, but not how those commands change the 3D world. The aligned demonstration clip contains this missing supervision because its $K$ frame transitions record the geometry, motion, visibility, and camera change produced during the corresponding $K$ actions. We introduce Track4Action, a framework that distills this realized transition from a frozen world-centric 3D tracker into a current-observation VLA policy. During training, Track4World encodes the clip $V_{t:t+K}$ into a pooled tracker feature. Learnable track queries infer this feature from current VLA hidden states, match it in a shared space, and condition a flow-matching action head through a feature-wise gate. The tracker feature only defines the alignment target, so neither the clip nor the tracker is used at deployment. Track4Action reaches 82.3% on zero-shot LIBERO-Plus, improving the alignment-free variant by 7.6 points and LaMP by 3.0 points. It obtains 80.44% and 81.48% on the clean and randomized RoboTwin 2.0 splits, and 67.5% average success across four physical bimanual tasks, 25.0 points above the alignment-free variant. The gains across simulation and physical tasks support action-aligned 3D tracker features as privileged supervision for tracker-free VLA deployment. Our project page is available at https://wing0night.github.io/track4action-project-page.

Dynamic 3D scene reconstruction has achieved remarkable success under the assumption of strictly synchronized multi-camera inputs. However, in real-world scenarios, temporal asynchrony among capturing devices remains a critical challenge, leading to severe motion blur and geometric artifacts. Existing asynchronous reconstruction methods typically estimate temporal offsets through photometric supervision, but appearance matching provides weak temporal cues under large offsets and complex motions. We attribute this limitation to two major bottlenecks: texture-induced collapse, where low-texture regions provide nearly vanishing alignment signals, and deformation-induced coupling, where temporal errors are absorbed into distorted geometry or motion rather than being explicitly corrected. To address these issues, we propose ASTRA (Asynchronous Spatio-Temporal Reconstruction via Trajectory Alignment), a framework that introduces 2D motion trajectories as explicit, texture-agnostic supervision for asynchronous dynamic reconstruction. Instead of synchronizing cameras solely through rendered color residuals, ASTRA jointly optimizes temporal offsets and dynamic 3D representations by aligning the projected motion of reconstructed 3D points with observed 2D trajectories, while using dynamic and certainty masking to suppress unreliable trajectory constraints. Extensive experiments on different dynamic Gaussian Splatting backbones show that ASTRA preserves high-frequency spatial details and sustains strong robustness even under severe asynchrony with up to 25-frame offsets, achieving approximately 1.4 dB PSNR improvement, reducing temporal-offset MAE by 54.0%, and nearly quadrupling the synchronization success rate.

Vision-language models (VLMs) are emerging as a key component of embodied intelligence, with growing applications in auto-labeling and end-to-end autonomous driving. However, existing approaches for improving spatiotemporal reasoning in VLMs often rely on complex preprocessing pipelines, expensive human annotations, or synthetic data, which limit scalability and introduce potential sim-to-real gaps. Moreover, although these methods have improved spatiotemporal understanding, they still lack strong metric reasoning capabilities for dynamic scenes, such as estimating object motion in real-world units. Prior work has explored LiDAR-based metric depth supervision to enhance spatial perception, but it does not directly address temporal reasoning. We introduce STAR-VLM, an automotive radar-supervised framework that enhances spatiotemporal VLMs with motion reasoning and metric velocity estimation for autonomous driving. Automotive radar is a low-cost and widely deployed sensor that provides complementary spatiotemporal supervision through range and Doppler measurements. By leveraging these measurements as label-free ground truth during training, STAR-VLM improves the metric spatiotemporal reasoning ability of VLMs. Through experiments on driving scenarios, we show that STAR-VLM achieves state-of-the-art performance on both motion classification and metric velocity estimation, outperforming even task-specific methods designed for each task. These results highlight automotive radar as a scalable and cost-effective source of supervision for building metric-aware spatiotemporal VLMs for real-world autonomous driving.

Recent studies develop pixel-level multimodal large language models (MLLMs) that support both Region Segmentation and Region Understanding, extending multimodal interaction from whole images to specific objects and regions. However, these methods face two fundamental challenges. First, the scarcity of high-quality mask--text pairs leaves abundant mask annotations without corresponding language supervision. Second, discrepancies in supervision formats and learning-signal densities induce optimization interference between Region Segmentation and Region Understanding. To address these challenges, we propose PixVL, a self-supervised post-training framework that introduces a unified Mask--Text Consistency Cycle, enabling pixel-level MLLMs to generate and self-verify regional descriptions and learn from unlabeled data. We found that direct cycle based solely on geometric reconstruction is unreliable because re-segmentation IoU does not faithfully reflect the semantic quality and referring sufficiency. PixVL therefore introduces confuser-aware semantic verification, which uses the model's confidence when it correctly chooses the target among highly similar candidate regions, and assigns zero reward to an incorrect choice. Meanwhile, PixVL performs cross-view verification using temporally separated video frames or geometrically transformed image views, preventing cyclic learning from collapsing to positional and shape shortcuts. Finally, a quality-coupled bidirectional learning strategy uses the highest-reward description to guide Text-to-Mask learning. This strategy transforms Region Understanding and Region Segmentation from competing tasks into mutual generators and verifiers. Experiments demonstrate that PixVL improves both region understanding task and segmentation task.

We propose OC-VLA++, an extension of OC-VLA for viewpoint generalization under limited camera coverage. While OC-VLA grounds robot actions in the camera coordinate system to align action supervision with visual observations, camera-space grounding alone can still overfit to the few viewpoints observed during training. OC-VLA++ addresses this limitation by introducing geometry-guided paired-view supervision and an explicit cross-view action-equivariance objective. Given paired observations of the same manipulation scene from geometrically related viewpoints, the model is trained such that their camera-space predictions correspond to the same robot-frame action. This objective explicitly supervises how action predictions should transform across viewpoints, rather than relying solely on image-level augmentation. Experiments demonstrate substantial improvements in unseen-view generalization under limited camera coverage, with performance degrading more gracefully under increasing camera displacement. These results establish cross-view action equivariance as an effective complement to observation-centric action grounding for robust real-world deployment.

Recent subject-to-image models have achieved impressive progress in personalized image generation, yet they still struggle to preserve fine-grained subject-specific details. A major reason is the lack of high-quality fine-grained identity supervision: real paired data are expensive to collect, while synthesized training pairs often preserve only coarse subject appearance and fail to capture subtle subject-specific details. In this work, we propose CopyCat, a lightweight model-refinement framework that improves fine-grained subject consistency within only a few seconds. CopyCat performs a one-time refinement of a pretrained subject-to-image model by attaching a lightweight Fine-grained Consistency LoRA (FCLoRA) and optimizing it using a single proxy image, which is used as both the conditioning image and the reconstruction target. This exact self-reconstruction objective substantially simplifies the optimization task, enabling effective fine-grained refinement within only a few seconds. The refinement is performed only once; the resulting model can be directly applied to diverse unseen reference subjects and prompts without further subject-specific optimization. We further revisit subject-to-image LoRA training in double-stream diffusion transformers and find that adapting only the visual stream consistently improves subject consistency. Extensive experiments on DreamBench and XVerseBench demonstrate consistent improvements in fine-grained subject consistency across representative subject-to-image models under both single- and multi-subject settings.

World-Action Models (WAMs) augment robot policies with future visual prediction, but it remains unclear what the visual modality should learn for control. While photorealistic future prediction provides dense supervision, it also incurs substantial computation and can allocate capacity to texture, illumination, and background variations that are only weakly related to action selection. Recent efficient WAM variants suggest that the main benefit of the video branch may not lie in the rendered future itself, but in the control-relevant visual representations induced during training. In this work, we revisit future video prediction from a dynamic-centric perspective and ask whether an existing RGB-based WAM can be redirected from appearance-dominated reconstruction toward interaction-induced visual dynamics without introducing additional modality-specific predictions or online inputs at deployment. We propose DC-WAM, a dynamic-centric WAM framework that redistributes supervision and computation in the RGB video branch. At the supervision level, DC-WAM combines temporal-difference flow matching with trajectory-guided weighting, emphasizing dense temporal changes and localized regions where the gripper, manipulated objects, and contact areas move. At the reasoning level, DynaRoute predicts token-wise dynamic relevance and converts it into an attention bias, guiding the model toward control-relevant future tokens. Experiments in simulation and on real-world manipulation tasks show that DC-WAM consistently improves policy performance, especially under out-of-distribution perturbations in lighting, object appearance, and background texture.

While Large Vision-Language Models (LVLMs), represented by LLaVA and GPT-4V, have demonstrated remarkable capabilities, their visual inputs remain vulnerable to adversarial attacks, posing significant security risks. Existing defense methods predominantly target single-task scenarios (e.g., zero-shot classification) and consequently lack generalizability across various multimodal tasks. To address this limitation, we propose a dual adversarial fine-tuning framework that jointly optimizes visual and semantic supervision signals from two modalities, enhancing model robustness while generalizing across multiple downstream tasks. The proposed framework comprises two core components, i.e., $\textbf{Visual}$ supervision branch and $\textbf{Semantic}$ supervision branch. The former branch leverages features from clean images, extracted via a frozen original vision encoder, to guide adversarial robustness while the latter incorporates caption-image alignment as a contextual signal to preserve semantic coherence under attack. Moreover, our method achieves cross-task robustness by simply replacing the CLIP vision encoder in the original model, with no need of separate task-specific retraining or architecture modifications.Extensive experiments demonstrate that our approach outperforms the state-of-the-art method in adversarial robustness evaluation across zero-shot classification, image captioning, and visual question answering (VQA) tasks.

Accurate 3D--2D liver registration, which aligns preoperative 3D models to partial, view-dependent intraoperative surface observations, is critical for AR-guided laparoscopic surgery but remains challenging due to severe occlusion, limited visibility, and the lack of 3D ground-truth supervision. Existing landmark-free approaches perform partial-to-complete geometric alignment, yet robust self-supervision under extreme partial visibility remains difficult. We propose Vis2Reg, a visibility-aware registration framework that explicitly constrains deformation using mask-consistent visible regions. We introduce a visibility-aware self-supervision that derives a visible-domain 3D supervision signal from intraoperative masks, enabled by differentiable point rasterization and mask-guided back-projection. This formulation improves robustness under severe occlusion while maintaining fully self-supervised learning. Vis2Reg combines a robust geometric rigid initialization module with an implicit neural deformation field for stable alignment. Vis2Reg achieves a Dice score of 92.6% and a Chamfer Distance of 1.43 mm on real intraoperative datasets, with 111 ms per-frame inference time, demonstrating both accuracy and practical efficiency.

Weakly-supervised RGB-D Salient Object Detection (SOD) is explored to reduce the heavy burden of pixel-level annotations. But scribble annotations lack the structure and details of objects, resulting in inaccurate saliency maps. In this paper, we propose a novel scribble-supervised RGB-D SOD method, consisting of a Segment Anything Model (SAM)-driven pseudo annotation generation method (\emph{SAM-PAG}) and a state space interaction-based conditional diffusion model (\emph{$S^2$Diff}). Specifically, SAM-PAG is tailored to address the issue of sparse supervision information. In SAM-PAG, we adopt the advanced SAM to expand sparse scribbles to dense pixel-level pseudo annotations through the dual-branch structure and the consistency of segmentation masks. In $S^2$Diff, we adopt the diffusion model to iteratively refine the noisy saliency maps with the guidance of conditional information, generating accurate saliency maps. Naturally, the core of our $S^2$Diff lies in the acquisition of conditional features and the denoising of saliency maps. For the former, we employ a cross-modal conditional generation module to interweave cross-modal features through frequency integration and implicit-explicit state space interaction, effectively achieving global conditional features. For the latter, we employ a context injection module to mitigate noise interference and to enhance object information with the conditional context. With the close cooperation of SAM-PAG and $S^2$Diff, our method outperforms relevant scribble-supervised methods and achieves competitive performance compared to fully-supervised methods on seven datasets. The code and results of our method are available at https://github.com/Switch457/WeakS2Diff_SOD.

When a camera moves fast during exposure, blur destroys the intra-exposure motion a 3D model needs to recover the sharp scene, while event cameras capture exactly this signal at microsecond resolution. Turning them into reliable 3D supervision faces two obstacles. First, the two restoration priors fail in opposite ways: physics-based event-integration priors preserve edges but accumulate drift; learned networks recover texture but distort boundaries. Second, existing pipelines run in one direction only, so raw event noise or the biases of fixed 2D pseudo-labels pass uncorrected into the geometry. JADE-GS addresses both: a pixel-adaptive routing gate fuses the complementary priors, and the resulting 2D restorer is coupled to a 3D Gaussian Splatting student in a bidirectional loop, where detached, multi-view-consistent renders and a physics-based reblurring constraint regularize the restorer, turning a fixed preprocessor into a geometry-aware predictor. Across synthetic and real benchmarks, JADE-GS attains the best perceptual quality, leading LPIPS and CLIP-IQA on both benchmarks with competitive PSNR and SSIM, and trainsin about one hour under 5 GB on a single consumer GPU while preserving real-time rendering.

Self-supervision is a powerful technique for learning visual representations from unlabeled data. Existing techniques primarily adopt a two-stage approach for self-supervised learning (SSL): a pretraining stage on unlabeled data followed by a finetuning stage on labeled data. While this pipeline has demonstrated extreme effectiveness, the interaction between self-supervised and supervised learning objectives remains insufficiently understood. In this work, we systematically investigate whether jointly optimizing the self-supervised and supervised objectives during training provides a better alternative. We compare two training paradigms: (1) the aforementioned pretraining followed by finetuning (PFT) and (2) joint training (JT), where self-supervised and supervised losses are optimized simultaneously in the same network. Across eight representative SSL methods and diverse computer vision tasks on natural, medical, crisis response, and remote sensing data, we evaluate performance under varying percentages of labeled data. Our results reveal that the relative effectiveness of PFT and JT depends strongly on the task at hand, the availability of labeled data, and the complexity of the domain. We find that JT consistently improves data and training efficiency while being robust in low-label settings, while PFT is more reliable in more specialized domains. We further analyze representation quality, robustness, and cross-domain generalization, providing new insights into how self-supervised and supervised objectives interact during optimization. We establish a comprehensive empirical benchmark for hybrid SSL-based semi-supervised learning and offer practical guidance for selecting appropriate training strategies across diverse vision applications.

Referring Camouflaged Object Detection (Ref-COD) requires segmenting hidden targets guided by reference cues. While supervised methods are annotation-heavy and training-free approaches via sparse point-prompting are sensitive to localization errors, we propose GFR-SAM, a robust three-stage training-free framework. GFR-SAM shifts the paradigm from fragile point-matching to a "Generate-Filter-Refine" pipeline. First, we introduce In-Context Exemplar-guided Segmentation, empowering SAM3 with cross-image inference to generate candidate masks via holistic visual exemplars, bypassing its native intra-image constraints. Second, a Region-Global Contrastive Filtering module ranks candidates through DINOv3-based prototypical alignment, effectively suppressing background distractors. Finally, a Geometric-Semantic Refinement module synergizes bounding box and text prompts to recover fine-grained boundaries and enhance instance recall. Evaluated on the R2C7K benchmark, GFR-SAM outperforms existing training-free methods by 8.7% in weighted F-measure ($F_β^w$) and competes with supervised state-of-the-art counterparts. Ultimately, this work underscores the potential of unlocking SAM3's latent capability for cross-image In-Context prompting, establishing a robust, training-free paradigm that effectively bridges the gap between general-purpose foundation models and specialized, label-intensive perception tasks without the need for task-specific fine-tuning.

High-quality alpha mattes are notoriously expensive to annotate, creating a fundamental data bottleneck for deep image matting. While prior work attempts to reduce annotation cost using coarser labels like trimaps or masks, they remain reliant on costly per-pixel supervision, limiting scalability and generalization. In this work, we push the boundary further and ask: can we train an automatic matting model using only RGB images, with no manual annotation at all? We answer this by presenting SSMatte, a self-supervised framework that for the first time achieves performance on par with fully-supervised automatic matting. Our key insight is to decompose the problem into semantic anchoring and detail matting. SSMatte first generates a semantic matting prompt from frozen self-supervised ViT features by propagating class-token seeds via a novel, training-efficient semantic anchoring loss based on a generalized Rayleigh quotient. This prompt then anchors a detail matting network, which is optimized via a fixed-point-based loss that enforces alpha-RGB consistency. Extensive experiments show SSMatte outperforms prior weakly-supervised methods, matches the performance of fully-supervised models on portrait benchmarks, and demonstrates favorable scaling and generalization behaviors with additional data. Our work pushes automatic matting to an fresh, fully annotation-free paradigm. Code will be available.

In time-lapse fluorescence imaging, single-particle-tracking is a powerful tool to monitor the dynamics of objects of interest, and extract information about biological processes. However, tracked particles can be subject to occlusion and intermittent detectability. When these phenomena persist over a few frames, tracking algorithms tend to produce multiple tracklets for the same particle. In this work, we introduce self-supervised learning of visual features to compare tracked particles, and we exploit both visual and positional distances to robustly stitch tracklets representing the same particle. We demonstrate the performance of our stitching framework on time-lapse fluorescence sequences of Hydra vulgaris neurons. Results show high stitching precision, and reduction of errors made by previous algorithms on the same data by a factor of two.

3D Gaussian Splatting provides an explicit representation that jointly models geometry and appearance, serving as a scalable foundation for 3D representation learning. Existing pre-training methods for Gaussian representations, such as masked Gaussian reconstruction, primarily capture local structures but offer limited semantic supervision. In this paper, we propose GaussFusion, a multimodal pre-training framework for 3D Gaussian representations. GaussFusion integrates image and text supervision into masked Gaussian modeling through cross-modal semantic alignment, enabling the Gaussian encoder to learn both visual and language-level semantic information during pre-training. To better adapt masked modeling to the non-uniform distribution of Gaussian primitives, we further propose Gaussian Salience-guided Multi-scale Hole Masking (GSHM). GSHM constructs spatially continuous masked regions based on Gaussian salience. By applying hole masks at multiple scales, GSHM encourages the encoder to capture both fine-grained local patterns and broader structural dependencies. Extensive experiments on downstream tasks demonstrate that GaussFusion improves the transferability of Gaussian representations. Notably, GaussFusion outperforms Gaussian-MAE on ModelNet40 and ScanObjectNN (PB-T50-RS) by 0.61% and 3.85%, respectively.

Monocular-to-stereo conversion synthesizes stereoscopic content from 2D videos for immersive 3D experiences. In modern Depth-Image-Based Rendering (DIBR) approaches, stereo inpainting of disocclusions is the critical bottleneck. Training-based methods achieve superior quality but rely on scarce stereo pairs or synthetic data with domain gaps. We address this through the first self-supervised framework learning from monocular videos via cycle consistency. Our key contribution is the Geometric Reciprocity Theorem (GRT): under the nearest-neighbor DIBR formulation, the disocclusion mask when synthesizing a target view equals the mask of pixels lost when warping back from target to source, enabling analytical computation of test-time disocclusion masks directly from monocular images. This yields train-test consistency for the stated warping formulation, supporting self-supervised learning from unlimited monocular videos and substantial improvements over training-free and supervised state-of-the-art methods. Project page: https://visual-ai.github.io/grt/

While various works address reflective symmetry understanding in 3D data and images, pixel-level semantic left-right prediction of in-the-wild images remains challenging, due to certain difficulties including the lack of 3D information, occlusion, object pose variation, partiality, etc. In this work, we propose an unsupervised learning framework to tackle this challenge. Leveraging recent advances in vertex-wise semantic left-right understanding of 3D data, our unsupervised learning method jointly utilises 3D shape and image datasets to infer pixel-wise semantic left-right predictions in single-view images. In particular, we show that a medium-scale 3D shape dataset comprising mainly of human- and quadruped animal-like shapes, combined with diverse in-the-wild image data, are sufficient to achieve high-quality semantic left-right prediction in images, even for entirely unseen 3D object categories, such as cars or trains. Overall, our approach achieves superior performance in dense pixel-wise semantic left-right predictions on both rendered and in-the-wild image datasets when compared to existing state-of-the-art methods.

Active Speaker Detection determines whether a visible person in a video is speaking at each moment. While recent audio-visual fusion methods perform well on clean data, they degrade under real-world corruptions such as background noise, occlusion, or simultaneous modality degradation. We attribute this limitation to the absence of explicit consistency constraints that promote robust, semantically aligned representations across modalities. Without such guidance, models tend to learn fragile modality-specific shortcuts that fail under corrupted conditions. We propose $C^3$ASD, a multi-level consistency-driven framework with three complementary constraints: embedding-level inter-modality consistency aligns audio-visual representations during speech; sequence-level intra-modality consistency separates speaking and non-speaking clusters via track-aware contrastive learning; and prediction-level consistency stabilizes fusion through knowledge distillation. Extensive experiments demonstrate significant improvements under diverse audio, visual and joint corruptions, while maintaining competitive performance on clean data.

Feed-forward 3D models are commonly trained using either expensive geometric supervision or self-supervised photometric objectives, both of which provide incomplete learning signals. We introduce Vision-Language Reprojection Consistency (VLRC), a scalable auxiliary objective that exploits frozen vision-language representations as semantic multi-view supervision. Given a predicted 3D reconstruction, VLRC reprojects dense vision-language features across views and enforces feature consistency between corresponding image locations, requiring no additional 3D annotations. The objective integrates seamlessly with both self-supervised monocular reconstruction and supervised-pretrained feed-forward 3D models during unlabeled adaptation. By aligning geometry with language-grounded features, VLRC not only improves depth and camera estimation but also enables more coherent multi-view semantic fusion for open-vocabulary 3D scene understanding. Experiments on indoor and outdoor benchmarks demonstrate consistent gains in 3D reconstruction accuracy and zero-shot open-vocabulary 3D semantic segmentation.

Autonomous robots often need to move their camera before they can act: to inspect an object, reveal an occluded region, or obtain a view that responds to a user's intent. While vision-language navigation translates instructions to base motion and vision-language-action policies map instructions to manipulation actions, language-conditioned camera motion remains comparatively underexplored as a first-class action. We formulate language-conditioned camera motion generation: given a current RGB observation and a free-form natural-language intent, predict a relative target camera pose for the next observation. This task is inherently non-trivial: viewpoint changes are driven by latent perceptual intentions, and a valid motion may operate at different semantic granularity, from entering a room to looking around a corner, inspecting a visible object, or revealing an occluded detail. To model this structure, we mine multi-intention camera-motion supervision from egocentric video, pairing plausible intents and observation-gain descriptions with relative SE(3) target poses. We propose LIME, a vision-language camera-motion generator that combines an auto-regressive observation-gain output with a continuous flow-matching pose head. This design lets the model jointly predict what the next view should reveal while representing multi-hypothesis target views. Across experiments and downstream robotic tasks, we show that LIME can learn to actively choose camera poses from passive human video, turning ordinary egocentric recordings into supervision for intent-aware active perception.

Image encoders trained with LeJEPA can deliver strong features for downstream tasks, but, like other image-level self-supervised methods, typically require large training datasets. Aligning representations at the level of objects rather than whole scenes promises greater data efficiency, but doing this in a completely self-supervised way, effectively jointly partitioning a scene and representing its objects, is unstable: the two are locked in a cyclic dependency, partitioning requires meaningful representations, while meaningful representations require consistent partitioning. We sidestep this instability by taking object masks as given during training, using cheap, off-the-shelf SAM proposals. We extend LeJEPA - whose distributional anti-collapse objective ports naturally from whole images to variable-sized sets of objects - to align object-centric representations rather than whole images. An additional instance-separating loss, which treats other objects in the same scene as negatives, further boosts downstream performance. Across two model scales and 10-100% of COCO, object-level LeJEPA outperforms image-level LeJEPA on tracking (DAVIS), classification (ImageNet-1k), segmentation (ADE20k), and re-identification (NAVI).

Egocentric gaze estimation is commonly studied using models that process the full video with access to future frames, while real-world applications require strictly causal, online prediction. This discrepancy raises key questions: Does future context inherently provide valuable signals for gaze estimation? If so, how much future look-ahead optimally supervises a causal model during training? To investigate, we propose a controlled framework featuring a future-aware branch that accesses a tunable look-ahead horizon during training but is discarded at inference. This design isolates the impact of future context while keeping the inference architecture fixed and strictly causal. Across EGTEA Gaze+ and Ego4D, we find that future-privileged supervision consistently improves causal gaze prediction, confirming its utility. However, performance gains do not increase monotonically with longer look-ahead, but rather peak within a bounded temporal regime. Specifically, optimal performance corresponds to roughly 1.7--3.3 seconds of future context ($H{\in}[5, 10]$) on EGTEA Gaze+ and 2.7 seconds ($H{=}10$) on Ego4D. Our results demonstrate that lightweight causal models can effectively absorb future-aware signals, providing practical guidance for real-time egocentric gaze modeling.

Video anomaly understanding (VAU) relies on sparse, context-dependent cues. However, existing passive paradigms suffer from observational aliasing, where static sampling fails to disambiguate semantically distinct events. To overcome this, we propose $Anom\text{-}π$, a closed-loop framework that reconceptualizes video understanding as an active sequential decision-making process within a dynamic environment. Inspired by human video-reviewing behavior, this framework unifies internal cognitive reasoning and strategic evidence acquisition into an interleaved policy, utilizing temporal atomic operators such as local backtracking, temporal expansion, and fine-grained sampling to endow the model with perceptual proactivity. To learn such complex interaction strategies under video-level weak supervision, we design Interactive Direct Preference Optimization (iDPO) to achieve trajectory-level policy alignment, guided by an Active Evidence Inquiry (AEI) utility that balances task success, informative evidence acquisition, and interaction cost. This approach enables the agent to learn to actively disambiguate hypotheses while suppressing redundant exploration. Extensive experiments demonstrate that our framework, with only 2B parameters, achieves highly competitive performance, significantly outperforming state-of-the-art large-scale VAU models in complex scenarios.

We introduce Point-supervised Multi-Object Tracking (PS-MOT) as a cost-effective alternative to traditional bounding box supervision, shifting the focus from spatial fitting to topological center-driven representation. However, PS-MOT faces challenges, e.g., spatial ambiguity and identity drift due to the lack of explicit geometric structure and scale constraints. To address these, we propose PS-Track, a hierarchical pipeline transitioning from points to instances across data, model, and loss levels. At the data level, we introduce Temporal-Feedback Prompting (TFP) to evolve points into temporally consistent pseudo-labels using negative spatial cues and motion priors. At the model level, we design the Point-Excited Wavelet Attention (PEWA) module, which leverages semantic correlations to activate high-frequency components, ``hallucinating'' object boundaries. At the loss level, Uncertainty-Guided Gaussian Learning (UGL) models pseudo-labels as probabilistic distributions, dynamically calibrating supervision intensity. Experiments on DanceTrack, EmboTrack, SportsMOT, and JRDB demonstrate that PS-Track provides a feasible and effective point-supervised alternative across diverse tracking scenarios, establishing a new state-of-the-art for point-supervised tracking. The source code is available at https://github.com/xifen523/PS-MOT.

Motions of objects and scenes carry essential intelligence in video understanding, offering rich cues for interpreting dynamic settings and interactions. Due to the cost and scarcity of high-quality annotation or ground truth of pixel-wise optical flow, however, motion estimation models are typically trained in synthetic domains while deployed in real-world domains. Addressing synthetic-to-real domain generalization challenges has been crucial for developing practical solutions in diverse open-world use cases. This paper introduces SciFlow, a simple yet effective, network-agnostic, training-based approach that leverages self-supervised learning to generalize motion estimation across synthetic and open-world domains. Specifically, SciFlow imposes semantic interference from open-world images onto synthetic images during training, blending indomain features with cross-domain interference, which enables the network to adapt to the real-world domains. Additionally, SciFlow utilizes geometric consistency to ensure validity of the self-supervision. Our experiment results show that SciFlow not only significantly enhances model robustness amidst domain variations, but also remarkably enables synthetic-to-real domain generalization without requiring any ground truth in the open world.

Effective multi-task learning for surgical scene understanding is fundamentally hindered by annotation granularity mismatch; temporal workflow tasks such as phase recognition, step recognition and anticipation benefit from dense frame-level supervision, whereas pixel-level spatial tasks including instrument segmentation and action recognition are only sparsely annotated on selected keyframes due to prohibitive labeling costs. This supervision imbalance undermines shared representation learning and limits joint optimization across heterogeneous surgical tasks. To address this, we propose Flow-guided Annotation for Robust Operating Scenes (FAROS), a flow-guided label interpolation framework, that combines zero-shot segmentation-based mask propagation with optical flow estimation to overcome the limitations of appearance-based propagation under challenging surgical conditions such as occlusion, smoke, and motion blur, generating temporally consistent dense pseudo labels from sparse keyframe annotations. The densified instrument masks and action labels are integrated into a unified Transformer-based multi-task framework that jointly learns surgical phase recognition, step recognition, anticipation, instrument segmentation, and action recognition, enabling balanced optimization between dense temporal supervision and sparse spatial supervision. The label interpolation quality of FAROS is first validated on the DAVIS 2017 benchmark under a sparse ground-truth protocol, confirming robust propagation beyond the surgical domain. Extensive experiments on GraSP, MISAW, and AutoLaparo benchmarks further demonstrate that FAROS significantly improves cross-task representation learning and enhances holistic surgical scene understanding performance across spatio-temporal tasks.

Vision-Language-Action (VLA) models require large-scale video-action pairs, yet real teleoperation remains scarce. While generated robot videos offer a scalable alternative, existing methods treat them as real robot data by recovering pseudo-actions from synthesized pixels. We argue that deriving low-level control from generated visuals is a mismatched abstraction. A video captures only \emph{geometry}: the spatial trajectory representing the \emph{where} of a task. A real demonstration captures \emph{control}: the exact motor commands representing the \emph{how}. Human-to-robot video generation preserves these unequally: the visible geometry survives the generation process, while the underlying control signals are lost. This \textbf{Asymmetric Preservation Principle} dictates a clean rule: this surviving geometry should solely supervise visual perception, leaving control to real demonstrations. Following this principle, we propose \textbf{GRA} (\textbf{G}eometry-guided \textbf{R}epresentation \textbf{A}lignment), which extracts the geometric content as future 2D end-effector waypoints, computed from the source human video through pose estimation, retargeting, simulation, and calibrated projection, and routes them to the VLA vision backbone via an auxiliary 2D head. The action head is trained on real demonstrations only. During fine-tuning, the waypoint loss persists as a \textbf{spatial representation anchor} that prevents the backbone from losing its geometric grounding. On real-robot tasks, GRA outperforms pseudo-action baselines under matched data budgets and narrows the gap to policies trained with substantially more real demonstrations, suggesting that correctly routed geometry bridges generated videos to robot policies more reliably than recovered actions.

Although text-to-motion generation has achieved strong progress in synthesizing realistic single-person motions from language, extending it to text-driven 3D human-human interaction (HHI) remains non-trivial, as HHI requires modeling the underlying \textbf{social structure} that governs phase progression, actor roles, and inter-actor coordination. In this paper, we formulate HHI generation as a social structure modeling and grounding problem: the model must first infer how an interaction unfolds and how the two actors coordinate their roles, and then realize this structure as continuous, physically plausible, and partner-aware 3D motion. To study how such structure should be modeled, we first examine the capability boundary of large language models (LLMs) for HHI generation. Our analysis shows that LLMs can \textit{think} by recovering phase decompositions and partner-aware roles, but cannot directly \textit{move}, as they fail to generate dynamic, physically plausible, and interaction-aware motion. This motivates our planner-executor paradigm, \textbf{Think with LLM, Move with Motion Skill}. The LLM planner converts implicit interaction semantics into motion-aligned social supervision by decomposing interactions into phases, assigning partner-aware actor roles, and aligning them with motion sequence. The motion executor then grounds the planned social structure into coordinated two-person motion by adapting a pretrained solo motion model with LoRA, previous-phase self-conditioning, and ego-relative partner conditioning. Together, our Solo-to-Social framework bridges social organization and motion realization, producing 3D HHI with improved phase consistency, role alignment, and partner-aware coordination.

Imperfectly supervised video polyp segmentation (VPS) aims to learn dense, temporally consistent masks from inexpensive supervision, including weak annotations (points, scribbles) and semi-supervision with few densely labeled frames. This setting is clinically valuable but challenging due to weak contrast, ambiguous boundaries, motion blur, and specular highlights, compounded by sparse pixel-level guidance. While SAM2 can generate dense masks from sparse inputs, direct pseudo-labeling often yields geometry-degraded masks with boundary leakage, underutilizes temporal consistency, and ignores reliability. To address these issues, we propose ARTEMIS, a unified framework for imperfectly supervised VPS driven by agent-guided reliability-aware temporal mask evolution. ARTEMIS initializes coarse masks from available supervision: SAM2 converts points/scribbles, while dense labels serve as reliable anchors. A debate-and-judge vision-language agent selects reliable temporal anchors under weak supervision, which are propagated bidirectionally with SAM2 to refine unreliable or unlabeled frames. Finally, ARTEMIS trains the segmenter using temporal reliability-aware robust learning, incorporating reliability-guided reference selection, a Reference Prototype Transport Module, and reliability-aware robust loss. These components assess mask reliability, evolve anchors over time, transport target identity across frames, and down-weight noisy supervision instead of discarding difficult samples. Experiments on SUN-SEG and CVC-ClinicDB-612 under scribble, point, and limited-label settings demonstrate that ARTEMIS achieves state-of-the-art performance. Code will be released at https://github.com/wangtong627/ARTEMIS.

We propose triangular consistency as a first-principled constraint for optical flow, which is agnostic to network architecture, supervision type, and dataset, and applies to both image-pair and multi-frame settings. This simple but powerful constraint is to compose two flows to induce a third flow and enforce consistency among the three. The composed flows may arise from (i) image pairs, yielding cycle consistency; (ii) multiple video frames, producing longer-range motion through temporal chaining; or (iii) image pairs combined with controlled synthetic transformations, which becomes data augmentation. This triangular consistency introduces negligible computational overhead and requires no additional annotations. Since it is derived directly from the geometry of optical flow, it does not rely on model-specific assumptions and serves as a ``universal'' plug-and-play component for optical flow training. Experiments show consistent improvement across supervised, unsupervised, and transfer learning settings.

Unlocking the spatial intelligence of multimodal large language model (MLLMs) is crucial for understanding and interacting with the 3D world. Prevailing approaches typically inject spatial priors via external tools, which impose significant inference overhead, or rely on latent feature distillation, which remains uninterpretable and lacks fine-grained geometric constraints. To address these issues, we propose SpatialSV, a framework designed to internalize robust 3D spatial awareness within MLLMs while simultaneously offering inherent interpretability. Deviating from passive feature imitation, SpatialSV employs task-oriented visual supervision, compelling the model to actively lift its 2D visual features into explicit 3D representations, including depth maps, camera poses, and point clouds. Crucially, this 2D-to-3D lifting process provides a transparent window into the model's representations: the resulting 3D reconstructions serve as an intuitive proxy for visualizing and diagnosing the quality of the model's intrinsic spatial knowledge. Extensive experiments across multiple models and benchmarks demonstrate the effectiveness of SpatialSV in enhancing and interpreting MLLMs' spatial intelligence. Furthermore, the framework exhibits strong generalization in semi-supervised settings, validating its potential to leverage unlabeled visual data for scalable, interpretable spatial representation learning.

UI videos provide a natural input for generating interactive webpages, as they capture both webpage appearance and action-triggered state transitions. However, directly applying video-capable vision-language models to this task remains insufficient. Existing models typically rely on sparse sampling or compressed temporal representations, which may miss short action boundaries and break the state-action-state transitions needed to implement webpage behavior. We formulate UI video-to-code generation as executable state-transition recovery from interaction videos, and identify this failure mode as state-transition misalignment. We introduce Video2Code, an action-aware video-to-code approach for recovering executable UI state transitions. Rather than allocating the visual budget uniformly across the video, Video2Code first performs coarse video understanding to locate action-critical regions, then invokes a temporal clipping tool to revisit these regions at higher temporal resolution before generating HTML/CSS/JavaScript code. We instantiate Video2Code with action-aligned video-code supervision and evaluate it under both visual and functional criteria. Experiments show that Video2Code substantially strengthens the underlying open-source model for UI video-to-code generation, improving functional correctness over direct video observation, especially on dense multi-step interactions.

Estimating human proficiency from video is a key challenge for automated skill assessment, with applications in sports coaching, music pedagogy, surgical training, and workplace learning. Existing approaches often focus on individual scenarios or rely on shared multi-view aggregation, limiting their ability to adapt to heterogeneous camera viewpoints and activity domains. We introduce SkillMoV, a unified, parameter-efficient framework for multi-scenario proficiency estimation from synchronized multi-view video. At its core, SkillMoV introduces a Mixture-of-View Projector (MoVP), which adapts the mixture-of-experts paradigm to camera-specific view features. MoVP is composed of four stages: (i) a Mixture-of-View soft router with twelve expert MLPs that learns view-dependent expert preferences without camera-identity supervision; (ii) cross-view attention to align synchronized cameras; (iii) learnable prototype anchoring to condition the representation on class-level reference vectors; and (iv) a prototype-conditioned gated projection that produces the final skill embedding. We evaluate SkillMoV on EgoExo4D across six skill domains and three separately trained view configurations: Ego, Exos, and Ego+Exos. SkillMoV reaches 50.17% overall accuracy in the Exos setting with a single model trained jointly across all scenarios, surpassing the strongest reported Exos result among the compared methods by 3.57 percentage points. In Ego+Exos, SkillMoV remains close to the best reported result in that setting (47.63% versus 48.20%). Ablations on the selected Exos configuration validate each component: MoV routing contributes +6.61 pp over attentive aggregation, cross-view attention +4.92 pp, prototype anchoring +4.07 pp, and stochastic view dropout +3.90 pp. Through LoRA adaptation, SkillMoV trains only 23.32% of its parameters and adds limited measured overhead relative to a LoRA-only baseline.

Generating novel renderings of a scene along user-defined camera trajectories from a single monocular video, dubbed video retaking, is a compelling but difficult problem in content creation and visual effects. Existing geometry-guided approaches reconstruct a 4D representation from the source video and render it along the target trajectory to condition video diffusion models. However, this guidance degrades as the target camera departs from the source trajectory, leaving newly revealed regions sparse or entirely missing. We propose SierpinskiCam, which addresses this limitation by augmenting geometry-based guidance with Sierpinski dome texture cues that contains rich trackable features even under large viewpoint changes. We further introduce a reference video conditioning mechanism that appends source-video tokens to the target-token sequence and separates the two streams with negative RoPE indices, enabling appearance grounding without architectural modification or per-video adaptation. Extensive experiments show that SierpinskiCam achieves significant gains in camera controllability, geometric consistency, and video quality across diverse and challenging retaking scenarios. Project page: https://hyelinnam.github.io/SierpinskiCam/.

Progress in AI has largely been driven by methods that assume less. As compute and data increase, approaches with weaker inductive biases generally outperform those with stronger assumptions. This is particularly characteristic of the field of Visual Representation Learning, where approaches have gone from being dominated by Supervised Learning, to Weakly Supervised Learning, to the now widespread success of Self-Supervised Learning without human labels. Yet, even modern Self-Supervised Learning approaches still depend on strong inductive biases such as augmentations, masking, or cropping. If this trend holds, even these remaining biases should become bottlenecks at scale -- and our experiments confirm this: the optimal strength of inductive biases decreases as data grows. This motivates the search for approaches that rely on fewer assumptions. To this end, we introduce Temporal Difference in Vision (TDV), a new paradigm for self-supervised learning from video that avoids existing inductive biases, relying instead on a causal assumption that the past causes the future. TDV functions by jointly training an image encoder and a motion encoder so that the current frame's representation plus the encoded motion equals the next frame's representation. Despite not leveraging any strong inductive biases, TDV matches state-of-the-art recipes on dense spatial tasks, laying the foundation for representation learning without strong assumptions.

Reliable monocular video depth estimation is crucial for downstream 3D reasoning and embodied AI in endoscopic navigation. However, existing self-supervised approaches typically treat video frames independently or rely on weak temporal regularization. These methods, lacking a holistic perception of the underlying 3D scene, inevitably suffer from geometrically inconsistent predictions and severe cross-frame drift. To address these limitations, we introduce a new paradigm that recasts sequential video depth estimation as an unconstrained multi-view 3D reconstruction problem, enabling full exploitation of the powerful geometric priors embedded in recent 3D foundation models. The core of our approach is a 3D consistency optimization framework driven by three constraints: image-level photometric rendering, explicit world-coordinate geometric alignment, and multi-scale temporal gradient consistency. Such unified optimization elegantly anchors isolated frames to a globally coherent 3D structure. Our method has been validated in both the self-supervised training scenarios and challenging zero-shot clinical environments. Results show that the proposed approach achieves state-of-the-art spatial accuracy, outperforming the frame-based, video-based depth estimators and the multi-view 3D reconstruction baselines.

In this paper, we introduce DenseControl, a novel pipeline for generating dense crowd images. Specifically, DenseControl meticulously positions and sizes each generated instance to align precisely with the predefined coordinates and scales. Based on this, we further allow for control over the background, style, and attributes of instances. The motivation behind DenseControl stems from the observation of two main challenges in synthesizing crowd images: controlling signal embedding and maintaining topological integrity when imparting instance scale guidance. To address these, we first introduce the Isolated Object Embedding (IOE) map, a novel representation that facilitates spatial location control while mitigating the difficulties associated with learning projections for model. Secondly, we propose an Implicit Scale Embedding (ISE) strategy that seamlessly integrates with the IOE map to encode precise scale information. To further enhance the efficacy of combining ISE with the IOE map, we incorporate a Position Shortcut mechanism that enhances cross-attention to alleviate projection challenges. We evaluate DenseControl through two lenses: synthesis quality and applicability in latent applications. Experiments across different control conditions demonstrate DenseControl achieves state-of-the-art results in dense crowd image synthesis. Furthermore, we showcase applications in augmenting crowd analysis under data scarcity, transfer learning, and weather generalization scenes, to highlight the practical utility of DenseControl. The codebase will be released.

Open-vocabulary scene sketch semantic segmentation aims to assign dense semantic labels to sparse line drawings based on flexible category vocabularies specified at inference time, without relying on pixel-level annotations during training. Unlike natural images, sketches lack texture and color cues, making semantic understanding heavily dependent on stroke layout and spatial configuration, a challenge that renders single-layer vision-language features inherently unstable. Our key observation is that attention maps from different Vision Transformer layers encode complementary spatial cues: shallow layers capture global structural layouts, while deeper layers focus on local stroke intersections and object parts. This suggests that cross-layer aggregation provides a more robust structural prior than any individual layer alone. Leveraging this insight, we propose a structure-aware framework built upon \textbf{L}ayer-wise \textbf{A}ccumulated \textbf{S}tructural \textbf{A}ttention (\textbf{LASA}), which aggregates multi-layer attention to guide hierarchical semantic alignment under weak supervision and refine predictions during inference. Experiments on FS-COCO, SFSD, and FrISS show that LASA improves mIoU by $+3.43$, $+8.01$, and $+15.74$ over the prior weakly supervised baselines, demonstrating consistent gains in both segmentation accuracy and spatial coherence. Our source code will be made publicly available.

Forecasting the future evolution of dynamic scenes is crucial in autonomous driving. However, existing feed-forward paradigms are primarily designed for interpolation. When extended to future extrapolation, they suffer from ghosting artifacts under large displacements and are constrained by simplified motion assumptions or strict future priors. To overcome these challenges, we propose Envision4D, a fully self-supervised feed-forward framework for pose-free future extrapolation. Specifically, we introduce a Future Pose Prediction module that infers future camera parameters via an iterative denoising process. Furthermore, to capture non-linear dynamics, we propose In-layer Temporal Attention and employ Conditioned Motion Lifting, which transforms the highly uncertain extrapolation process into robust relational mappings. Finally, a Progressive Training Strategy is utilized to stabilize unsupervised motion learning against error accumulation. Extensive experiments demonstrate that Envision4D achieves state-of-the-art performance, significantly outperforming existing methods in future view synthesis.

Generating complete 3D scenes from a single image requires inferring globally consistent geometry, object relationships, and environmental context from inherently ambiguous visual evidence. Despite recent progress in joint layout-and-mesh generation, existing methods often rely on holistic or weakly decomposed pipelines that entangle many factors at once and demand extensive scene-level supervision, limiting their generalization to complex real-world environments. We propose a multi-agent orchestration framework that decomposes single-image 3D scene generation into three structured stages: scene initialization, environment construction, and multi-agent refinement. The initialization stage extracts image-derived object masks, builds object-level 3D representations, and predicts an initial spatial layout to form a coarse 3D scene. The environment-construction stage then leverages this initialization together with point-map geometry to build an environmental scaffold of supporting surfaces, room boundaries, materials, and illumination. Finally, in the refinement stage, a planner agent identifies structural and visual inconsistencies, applies simple corrections directly, and dispatches specialist agents for complex localized revisions that are reintegrated into the global scene. To provide reliable structural initialization while reducing reliance on scene-level annotations, we further introduce a geometry-aware layout predictor supervised by sparse geometric priors derived from point maps. Unlike fully supervised layout generators, the predictor can be trained from segmentation-level data and generalizes robustly to diverse real-world scenes. Extensive experiments on benchmark datasets show that our method consistently outperforms prior approaches in geometric accuracy, spatial consistency, and perceptual realism.

Weakly Incremental Learning for Semantic Segmentation (WILSS) suffers from the continuous introduction of noisy supervision, which progressively corrupts class-level representations, leading to severe feature drift and semantic corruption, thereby causing newly learned classes to overwrite old ones. To address these issues, we propose a drift-resilient WILSS approach, named SASA, designed to stabilize semantic learning via Semantic Anchors and Spatial Arbitration. Specifically, at the representation level, we introduce semantic anchors of learnable tokens as rigid class-level references to preserve long-term semantic identity. Complementary to this, an elastic residual adaptation facilitates controlled, instance-specific refinement, ensuring a stable yet flexible learning trajectory. At the supervision level, we develop a Spatial Label Arbitration mechanism that performs geometry-aware decisions to directly filter unreliable signals and enforce a strict "one object, one class" constraint. By synergistically stabilizing representations and improving supervision reliability, SASA effectively mitigates feature drift under weak supervision. Extensive experiments on standard benchmarks demonstrate that our approach consistently outperforms existing state-of-the-art methods, particularly in challenging multi-step incremental settings. The code is available at https://github.com/ZhonggaiWang/SASA.

Dynamic 3D Gaussian Splatting (3DGS) methods reconstruct time-varying scenes from synchronized multi-camera video using photometric supervision. When a moving object becomes fully occluded from all training cameras, this supervision vanishes: the Gaussians representing it receive no gradient signal and degrade. Existing approaches to incomplete observations in neural reconstruction rely on learned generative priors that prioritize visual plausibility over physical correctness. We propose $\textbf{PersistGS}$, a method that restores object permanence during occlusion by coupling differentiable rigid body simulation with 3D Gaussian Splatting. Our approach decomposes the scene into per-object Gaussians and collision meshes, estimates friction and velocity from the observed pre-occlusion trajectory via differentiable simulation, and uses the resulting SE(3) trajectory to position object Gaussians throughout the occlusion period. Because the predicted trajectory satisfies the governing equations of rigid body dynamics, it faithfully captures contact events (bounces, friction-based deceleration, direction changes) that kinematic extrapolation cannot model. We introduce a centroid silhouette loss that isolates positional gradients from appearance noise, yielding 40% lower trajectory error than photometric supervision. We evaluate using cameras withheld from training that observe the object during its occlusion. Experiments on synthetic scenes show that PersistGS outperforms constant velocity extrapolation by +2.46dB PSNR and comes within 0.19dB of a ground-truth trajectory upper bound.

Self-supervised novel view synthesis (NVS) remains challenging to scale, despite the abundance of video data, largely due to the brittleness of training on realistic videos and the hard-to-predict scaling behavior of multi-network system designs. We introduce RayDer, a unified, feed-forward transformer that consolidates camera estimation, scene reconstruction, and rendering into a single backbone, turning self-supervised NVS into a well-posed single-model scaling problem. A minimal dynamic state, treated as a nuisance factor, absorbs time-varying content and enables stable training on unconstrained real-world video. Importantly, RayDer keeps static-scene NVS as its target task: dynamic content is leveraged purely as scalable supervision, not reconstructed as in dynamic-scene (4D) NVS. Across multiple model sizes and orders of magnitude in data, RayDer exhibits clean power-law scaling with data and compute, and outperforms static-scene data mixtures. On a large number of benchmarks, RayDer achieves strong zero-shot open-set performance competitive with state-of-the-art supervised approaches. Project Page: https://compvis.github.io/rayder

Detecting covariate shift is critical for building reliable vision systems. While most prior work focuses on improving robustness to shift, explicitly detecting covariate shift remains underexplored. Existing approaches typically rely on fully supervised training, requiring labeled examples from both original and shifted distributions, which is often impractical. In this paper, we show that covariate shift detection can be effectively addressed with weaker supervision using Positive Unlabeled (PU) learning. However, under covariate shift, in distribution and shifted data overlap significantly, making classical PU methods unstable and sensitive to noise. To overcome this challenge, we introduce Spectral PU Neighborhood Annotation (SPUNA), a geometry aware framework that progressively discovers shifted data by leveraging the local manifold structure of visual features. Extensive experiments show that SPUNA achieves state of the art performance in PU settings and remarkably matches the performances of fully supervised methods. Moreover, our approach transfers robustly across different types of shifts, demonstrating strong generalization capabilities.