Large Inter-Frame Displacements

Current dense visual SLAM systems rely almost exclusively on 8-bit tonemapped Low Dynamic Range (LDR) inputs, limiting their robustness in extreme lighting where shadows and highlights trigger tracking drift and mapping collapse. Conversely, existing raw and High Dynamic Range (HDR) reconstruction pipelines operate strictly offline. They depend on Structure-from-Motion preprocessing and are not suited for large inter-frame motion. We present, to the best of our knowledge, the first online Gaussian SLAM framework that tracks and maps directly on single-exposure 16-bit linear HDR imagery. Our method rests on three core components: an architecture-agnostic HDR Gaussian Splatting module featuring an MLP-free logarithmic parameterization of Gaussian color features; a Reinhard range-compressed photometric objective; and structure-guided spatial gradient weighting. Combined, these components allow our approach to outperform a direct HDR adaptation of MonoGS in both trajectory and reconstruction accuracy, while rendering natively in linear scene radiance for post-rendering processing. The same formulation runs unchanged on standard 8-bit inputs, roughly halving the MonoGS baseline error. Furthermore, our HDR Gaussian module transfers seamlessly to SplaTAM, Gaussian SLAM, and DROID-W, eliminating all tracking failures these systems suffer on challenging illumination sequences. To enable this research, we introduce RawSLAM: a dataset of 10 real-world indoor sequences featuring 16-bit RAW imagery, aligned depth, IMU measurements, and external OptiTrack poses. Code and dataset will be made publicly available soon.

Training-free, camera-controlled novel view synthesis from a single image using pre-trained video diffusion models often becomes unstable under large camera motion and long generation horizons. Existing approaches commonly combine several inference-time components, making it unclear which design choices are most important for stability. We show that the main source of stability is simple. Decomposing camera motion into small autoregressive steps limits per-step geometric distortion and reduces error accumulation. A controlled camera-step study shows that performance remains stable for small motions and degrades more strongly as the per-step motion approaches $18$-$20^\circ$. We further evaluate geometry-constrained spatial attention and low-frequency appearance anchoring as supporting refinements, together with an efficient registration-free warping pipeline. Across RealEstate10K and MegaScene, CamTrol++ improves temporal and geometric consistency, downstream 3D reconstruction quality, and generation efficiency over training-free baselines. The method remains effective for 56-frame generation and under substantial controlled depth corruption. These results show that careful control of camera motion at inference time can substantially improve the stability of camera-controlled novel view synthesis without retraining or modifying the diffusion backbone.

Latent diffusion models have recently advanced video frame interpolation by synthesizing intermediate frames between input images. However, handling large temporal gaps and complex motion remains challenging, often resulting in motion blur, structural distortions, and temporal inconsistencies. Event cameras provide high-temporal-resolution motion cues that are well suited for bridging these gaps and improving interpolation quality. To exploit this advantage without training an event-assisted model from scratch, we propose an adapter-based framework that incorporates event-derived cues into a pre-trained image-to-video diffusion model with minimal architectural changes. Specifically, our method leverages Image Warped Events (IWEs) and bidirectional sparse optical flow to provide spatially and temporally aligned guidance during generation. By injecting these event-guided structural and motion cues into the diffusion process, our approach reduces interpolation artifacts and improves both reconstruction fidelity and temporal coherence. Experimental results on real and synthetic benchmarks show that our method consistently outperforms existing state-of-the-art approaches. The project page is at https://joseph-lin-tech.github.io/BridgeEventDiT-VFI/.

Visual object tracking requires effective temporal integration, yet most Transformer trackers still rely on predominantly feed-forward feature extraction. Existing temporal mechanisms typically update templates, prompts, queries, or prediction states, while intermediate representations are rarely reused to modulate corresponding processing stages. We propose \textbf{FeedbackTrack}, a visual-cortex-inspired framework that introduces sparse, group-level layer-aligned cross-frame feedback into pretrained Transformer trackers. Previous-frame intermediate states are detached, cached, and returned to corresponding Transformer groups in the current frame through two lightweight pathways: Query Feedback for token-level query modulation and Gate Feedback for context-dependent feature modulation. FeedbackTrack preserves the original tracking pipeline with only a fixed-size one-frame cache. Across SPMTrack and ARTrackV2, FeedbackTrack consistently improves five backbone configurations on LaSOT and GOT-10k, achieving 83.4 AO and 79.1 AUC with SPMTrack-G while adding less than 1% parameters. Controlled comparisons show that cross-frame feedback outperforms same-frame modulation by 1.8--3.2 AO points, demonstrating that the gains mainly come from recurrent historical information. Further analysis reveals a non-uniform depth-dependent organization of learned feedback strengths, highlighting the effectiveness of recurrent feedback for Transformer tracking.

Video restoration methods exploit temporal information to recover information missing from degraded observations. However, reference frames within the sequence may introduce inconsistent degradation, content discrepancy, or reconstruction errors due to physical image-formation variations, occlusion, and imperfect temporal aggregation. Existing approaches mainly focus on improving restoration networks, while the reliability of the generated outputs at different spatial locations remains largely unexplored. In this work, we propose ANCHOR, a model-agnostic framework that revisits the low-quality current frame as a temporally aligned anchor for video restoration correction. Specifically, ANCHOR estimates a spatial trust field from heterogeneous physical-trace evidence and adaptively balances the restoration proposal with the original observation. Experiments on High Dynamic Range video reconstruction and video deraining demonstrate consistent improvements across various state-of-the-art restoration models, validating the effectiveness of reliability-aware output correction for video restoration.

Current few-step autoregressive video diffusion models depend on previous fully denoised clean frames as context for all denoising steps of the current frame. However, these clean frames leak excessive local details, which causes the model to take shortcuts, resulting in compromised temporal semantics and dynamics. Inspired by the perspective of diffusion as masking, we explore the impact of noisy contexts on few-step autoregressive generation. Yet, simply applying contexts with the same noise levels provides insufficient guidance, leading to poor temporal consistency. To resolve this dilemma, we introduce In-Context Forcing, a progressive autoregressive paradigm that utilizes contexts with decreasing noise levels. By applying less masking to distant frames and more masking to adjacent ones, this approach provides adaptive guidance, effectively ensuring both robust temporal consistency and high inter-frame dynamics. Furthermore, by decoupling the strict dependence on previous clean frames, our paradigm enables cross-frame parallel denoising, achieving substantial inference acceleration without sacrificing performance. Extensive experiments on VBench demonstrate that our method significantly outperforms state-of-the-art approaches in both visual fidelity and inference speed.

Recent advances in 4D Gaussian Splatting (4DGS) enable high-fidelity, real-time spatiotemporal rendering, but expose a fundamental trade-off between motion expressiveness and storage efficiency. While anchor-based designs achieve compactness through anchor-level parameter sharing, their rigid uniform parametrization enforces fixed Neural Gaussian counts and feature budgets per anchor. Consequently, insufficient fidelity is addressed by excessive anchor density, rather than lightweight, targeted increases in Neural Gaussian count or feature capacity, resulting in memory waste. To overcome this rigidity, we introduce an adaptive-capacity anchor-based framework that dynamically allocates the representational capacity based on local spatiotemporal demands. Adaptive Anchor Cardinality varies the number of Neural Gaussians per anchor, concentrating primitives in regions of high geometric or motion complexity while suppressing redundancy. In parallel, Adaptive Anchor Feature Masking modulates anchor-level feature channels, assigning rich features to complex regions and lightweight representations to simpler ones. Experiments on MPEG, Panoptic Sports, and N3DV datasets demonstrate substantial storage reduction without degrading visual quality. Notably, on challenging MPEG sequences with complex motion, our method achieves up to 1.5x higher compression than state-of-the-art anchor-based methods while preserving comparable quality.

Vision-language models excel at image and video understanding but suffer from high inference latency due to the need to process thousands of tokens per image, limiting their deployment on resource-constrained edge devices and in real-time surveillance applications. This challenge is further amplified in video processing, where multiple frames must be analyzed simultaneously. Existing token reduction techniques are largely developed for single-image inputs and therefore fail to account for the temporal and inter-frame redundancies present in video sequences. In addition, these methods generally rely on a fixed, uniform pruning ratio applied across all inputs, which is suboptimal because the degree of redundancy can vary significantly between different videos, necessitating content-dependent pruning levels to preserve critical information. To address these limitations, we propose a two-stage adaptive token pruning strategy specifically designed for video processing. In the first stage, we prune out the redundant frames, and in the second stage, token-level pruning is applied within the retained frames. Crucially, the pruning ratio in the second stage is determined adaptively based on the content of each video. This is achieved by analyzing the correlation structure of token embeddings to quantify redundancy, which is used to determine the ratio. Importantly, our method is entirely post-hoc and requires no additional training or fine-tuning, while achieving strong empirical gains; notably, it improves accuracy by +7% on a video captioning benchmark at 10% token retention, while reducing computation TFLOPs by 95%.

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.

Archival film restoration is a challenging problem because historical footage contains compound degradations such as scratches, dust, blur, noise, flicker, and photometric aging, while clean reference videos are unavailable. Existing video restoration methods largely treat these degradations implicitly, reconstructing frames without explicit knowledge of where damage occurs or how severe it is. We propose DART, a degradation-aware recurrent transformer for archival film restoration. DART predicts and propagates a soft defect mask through time, using it to guide temporal fusion and condition the restoration network on both damage location and severity. This makes the restoration process explicitly aware of film artifacts rather than relying only on reconstruction losses. Experiments on real archival benchmarks show that DART improves no-reference perceptual quality over prior restoration architectures while remaining compact and efficient, producing cleaner and more temporally consistent restorations of structured film damage.

Autonomous driving requires understanding the road as a graph of drivable lanes and their connectivity, beyond the ego lane alone, to follow routes through intersections and reason about cross- and merging-traffic. Recent perception models infer such lane topology, i.e., lane segments together with their inter-lane connectivity (LCLC), from onboard sensors over a 360-degree BEV view. Due to neural perception's imperfections, their outputs retain structural instabilities such as missed detections, lost or incorrect LCLC, over-detection, and label flicker. This paper presents WASABI, a real-time post-processing pipeline that stabilizes lane topology outputs both within and across frames by treating lane segments and their LCLC connectivity as joint tracking targets, under onboard real-time constraints (10 Hz / 20 ms / up to 200 input lanes). The pipeline integrates segment tracking with connectivity, noise-robust topology-aware refinement, and a resource-constrained real-time design. On internal validation data (16 sequences), WASABI improves LCLC detection F1 from 0.834 to 0.948 (+0.114, +13.6%) and reduces centerline lateral error from 2.50 m to 0.95 m, while reducing detection false-positives by 24.6%. Temporal-stability metrics on the same data show LCLC toggle rate reduced by 63.3% and boundary-label flicker rate by 30.2%, confirming across-frame stabilization beyond per-frame accuracy.

Recent breakthroughs in 3D Gaussian Splatting (3DGS) have advanced neural rendering with high fidelity and speed. However, its performance degrades significantly in large-scale scenes due to the computational burden of tile-based rasterization. Existing optimization efforts either require costly scene re-training or focus on narrow aspects of the pipeline, overlooking critical inefficiencies in real-world deployments. Through a comprehensive analysis, we identify three primary sources of redundancy and low GPU utilization: redundant inter-frame pre-processing, viewpoint-based occlusion redundancy, and severe tile-level load imbalance. To address these issues, we propose CaT-GS, a novel and efficient 3DGS rendering pipeline. CaT-GS introduces a speculative multi-frame preprocessing method to eliminate redundant computations across consecutive frames, and an inter-frame caching mechanism to eliminate viewpoint redundant rendering stages. Furthermore, it refactors rasterization tasks with a dedicated kernel to mitigate tile load imbalance, significantly boosting GPU utilization. Extensive experiments demonstrate that CaT-GS achieves a speedup of up to 10 times over the original 3DGS and up to 70% over previous state-of-the-art methods, establishing a new benchmark for high-fidelity, real-time rendering of large-scale scenes.

Surgical video understanding is fundamental to navigation systems. Endoscopic perception is often hindered by a limited field-of-view and frequent instrument occlusions, making spatio-temporal context essential for robust inference. These challenges have motivated video models that aggregate information across frames. However, existing video models typically store past observations implicitly in learned feature representations, often requiring task-specific video training, substantial annotated data, and increased computational cost. We propose Stitch-Inferencer, a real-time, model-agnostic inference framework that replaces implicit feature memory with an explicit image-space panoramic canvas. By stitching valid observations across frames, Stitch-Inferencer preserves previously observed pixels in an online, instrument-free view, expanding the effective field-of-view and providing direct access to regions that are temporarily occluded or absent from the current frame. Downstream segmentation or tracking models are applied to a compact region of interest on the panorama, and their predictions are reprojected to the current frame, enabling existing models to exploit long-range context without retraining. Experiments on anatomy segmentation and point/box tracking demonstrate consistent improvements across diverse baselines while preserving real-time throughput. The stitching module alone runs at over 60 FPS, providing a practical inference-time solution to enhance endoscopic perception in computationally constrained intraoperative environments. Source code will be made publicly available.

Recent 4D Gaussian Splatting (4DGS) methods often fail under fast motion with large inter-frame displacements, where Gaussian attributes are poorly learned during training, and fast-moving objects are often lost from the reconstruction. In this work, we introduce Spatiotemporal Position Implicit Network for 4DGS, coined SPIN-4DGS, which learns Gaussian attributes from explicitly collected spatiotemporal positions rather than modeling temporal displacements, thereby enabling more faithful splatting under fast motions with large inter-frame displacements. To avoid the heavy memory overhead of explicitly optimizing attributes across all spatiotemporal positions, we instead predict them with a lightweight feed-forward network trained under a rasterization-based reconstruction loss. Consequently, SPIN-4DGS learns shared representations across Gaussians, effectively capturing spatiotemporal consistency and enabling stable high-quality Gaussian splatting even under challenging motions. Across extensive experiments, SPIN-4DGS consistently achieves higher fidelity under large displacements, with clear improvements in PSNR and SSIM on challenging sports scenes from the CMU Panoptic dataset. For example, SPIN-4DGS notably outperforms the strongest baseline, D3DGS, by achieving +1.83 higher PSNR on the Basketball scene.

Recovering high-quality video from sparse event streams is a challenging task. Regression methods often blur textures, while existing generative models struggle with long-term stability. We propose LongE2V, a novel approach that leverages pre-trained video diffusion priors to jointly handle event-based video reconstruction, prediction, and frame interpolation. By fine-tuning a foundational video model, our approach achieves high data efficiency and superior perceptual quality. We introduce Autoregressive Unrolling and Adaptive Context Switching to mitigate temporal drift in extremely long sequences. We also propose Reencoding Alignment with Cross Residual Correction to ensure precise bidirectional consistency during frame interpolation. Furthermore, Event Voxel Density Augmentation ensures robustness across varying sensor resolutions. Extensive experiments on real-world benchmarks demonstrate that LongE2V outperforms state-of-the-art methods across all three tasks, exhibiting exceptional temporal coherence and zero-shot generalization. Project page: https://cdfan0627.github.io/LongE2V-page/

Modern smartphones capture Live Photos, short video bursts surrounding a still image, offering a dynamic and engaging photographic experience. However, the cover photo and video components are generated by two distinct imaging pipelines: the photo stream undergoes full computational photography processing, while the video stream is constrained by real-time efficiency and heavy compression. This intrinsic separation produces a substantial quality gap in resolution, color fidelity, and dynamic range between the cover photo and video frames. When users reselect an alternative frame from the video to replace an imperfect cover, the chosen frame often suffers from severe degradation, making direct replacement visually unsatisfactory. Restoring such frames requires simultaneous enhancement of spatial detail and color appearance, a task considerably more challenging than ordinary super-resolution or color enhancement. To address this, we define the Live Photo Cover Frame Reselection and Enhancement (LPRE) task, which leverages the intrinsic cues available within each Live Photo: the high-quality cover image as a structural and color reference, the user-reselected low-quality frame as the reconstruction target and several adjacent video frames providing temporal cues. Building upon this formulation, we construct Live2K, a real-world dataset of 2,042 Live Photos, and develop a unified one-stage baseline that integrates multi-frame fusion, guided color enhancement and super-resolution, establishing the first benchmark for Live Photo enhancement research.

Reconstructing continuous 3D human poses from unconstrained videos is challenging, especially in extreme motion scenarios involving severe motion blur and occlusion. Current state-of-the-art methods typically rely on implicit temporal attention to aggregate features across frames. However, under severe visual degradation, input features often suffer from collapse, rendering them indistinguishable from noise. In such cases, implicit aggregation fails to distinguish valid signals, leading to catastrophic reconstruction errors. To address this robustness gap, we propose a simple yet effective framework called Anchor-guided adaptive inter-frame motion cues propagating (Again-Pose), reformulating pose estimation in degraded frames as a motion-guided recovery task. Instead of blindly smoothing features, we explicitly identify high-quality Anchor Frames based on feature saliency and propagate reliable kinematic cues to "inpaint" the poses of degraded intermediate frames. Specifically, a Dual-path Motion-aware Module captures fine-grained inter-frame dynamics, while a Difference-weighted Fusion Module adaptively propagates these cues to suppress drift. Extensive experiments on standard benchmarks (Human3.6M, 3DPW, PoseTrack) and the challenging FineDiving dataset demonstrate that Again-Pose significantly outperforms state-of-the-art methods in robustness and stability, effectively recovering plausible poses where other methods fail.

Accurately localizing and segmenting small targets in low signal-to-noise ratio (SNR) infrared sequences remains a challenging task. Since targets are often indistinguishable from the background in individual frames, existing methods, even when equipped with advanced foundation model and powerful inter-frame association mechanisms, still fail to detect them. Motivated by the observation that targets tend to emerge gradually from the background over time and become distinguishable, we propose Temporal-Emerged Prompting for Segment Anything Model (TEP-SAM), a principled framework designed to explicitly exploit such temporal-emerged cues to modulate and prompt SAM. TEP-SAM operates by jointly modeling global motion patterns and local motion deviations to locate potential targets. It further enhances target region features by leveraging motion discrepancy, thereby generating temporal-emerged cues for SAM and enabling non-interactive segmentation. By bridging large-scale semantic pretraining with task-specific temporal modeling, TEP-SAM effectively adapts SAM to the challenging multiframe infrared small target detection task. Extensive experiments demonstrate the effectiveness of our approach, particularly under severely low-SNR conditions and in complex dynamic background.

While Deep Unfolding Networks (DUNs) dominate video Snapshot Compressive Imaging (SCI), they remain constrained by a uniform design philosophy. Existing methods repeatedly stack high-complexity priors with identical structures, ignoring the fact that optimization trajectories converge toward static states. This results in representation stagnation, where high-cost computations are wasted on minimal feature updates. To address this inefficiency, we present Differential Unfolding (DU), a heterogeneous framework that replaces uniform repetition with dynamic evolution. Central to DU is the Differential Evolutionary Framework (DEF), which partitions the unfolding process into two complementary roles: structural anchoring and differential evolution. In this scheme, high-parameter general stages are sparsely deployed to generate high-fidelity feature foundations. Complementing these, lightweight differential stages employ a Differential Representation Prior (DRP) to propagate and refine these foundational features through a differential mechanism. By integrating Differential Representation Attention (DRA) for evolving attention maps and a Differential Modulated FFN (DM-FFN) for feature rectification, DRP effectively models cross-stage variations with minimal overhead. By focusing computational resources on dynamic evolution rather than static redundancy, DU achieves a superior trade-off between accuracy and efficiency. Extensive experiments verify that our method establishes new state-of-the-art results while significantly slashing computational overhead. https://github.com/Muyuan-Zhang/DU

Endoscopic video analysis is essential for gastrointestinal diagnosis and computer-assisted interventions, but video sequences are routinely degraded by specular reflections, motion artifacts, and missing frames. These transient corruptions can distract clinicians, reduce image interpretability, and disrupt downstream tasks such as 3D reconstruction and navigation. Effective restoration therefore requires methods that exploit temporal continuity rather than treating frames in isolation. We introduce a Gaussian Process Prior Variational Autoencoder (GPVAE) framework for endoscopic video restoration that replaces the standard factorized latent prior with a temporal Gaussian process prior, enabling interpolation of missing frames with uncertainty-aware reconstruction. The framework combines endoscopy-specific encoders, including a convolutional EndoVAE backbone and pretrained Vision Transformer encoders from GastroNet-5M, with two scalable GP approximations: Hierarchical Prior Approximation (HPA) and Sparse Precision Approximation (SPA). Specular reflections are handled using a DUCKNet-based masking pipeline that excludes corrupted pixels from the reconstruction objective. On the C3VDv2 colonoscopy dataset, the best GPVAE variants reduced image reconstruction RMSE by 21.9% on average, and by up to 26.1%, relative to matched VAE baselines. Downstream trajectory RMSE was reduced by 12.7% on average across classical visual odometry and a pretrained PoseNet, at an average increase of 27.3% in training time per epoch. Finally, the GP posterior provides per-frame uncertainty estimates that reflect temporal support and offer a confidence signal for restored frames.

We present a method for harmonizing the lighting of a foreground video to match a target background scene, adjusting shadows, color tone, and illumination intensity (relightful harmonization). Unlike images, acquiring labeled data for videos, where identical motions are recorded under different lighting conditions, is practically infeasible and non-scalable. While one way to create such paired data is to apply existing image-based harmonization models frame by frame to a video, the resulting outputs often suffer from significant temporal jitters. We overcome this problem by introducing a novel lighting deflickering model that can stabilize the global and local lighting flickering artifacts. Our video diffusion model learns from these upgraded deflickered data with a volume of real and synthetic videos to generate high-quality video harmonization results. We further propose an asymmetric alpha mask conditioning technique to learn the clean boundaries from real videos. Experiments demonstrate that our model achieves strong temporal coherence, naturalness, cleaner boundaries, and physically meaningful lighting behavior, while maintaining strong relighting expressiveness compared to prior image-based and video-based harmonization methods.

Infrared and visible video fusion is essential for achieving comprehensive perception in dynamic scenes. However, maintaining temporal consistency remains a formidable challenge. Conventional methods relying on optical flow often suffer from geometric rigidity and ghosting artifacts. Moreover, standard diffusion-based fusion models typically operate in a frame-by-frame manner; when extended to autoregressive settings, they lack intrinsic temporal constraints and are prone to severe error accumulation and drifting, where minor artifacts amplify over time. To address these limitations, we propose a drift-resilient video fusion method that reformulates the task as history-conditioned motion generation. We introduce Stabilized History Guidance and Soft Temporal Anchoring to reframe temporal consistency as spectral filtering, implicitly aggregating motion dynamics without rigid alignment. Furthermore, our Decoupled Structure-Motion Adaptation strategy bridges pre-trained priors and structural constraints via two-stage training and latent refinement. Extensive experiments demonstrate that our method achieves state-of-the-art performance in both fusion quality and temporal stability.

Visual geometry transformers have become powerful architectures for multi-view 3D reconstruction, enabling joint prediction of multiple 3D attributes in a feed-forward manner. However, their computational cost grows quadratically with the input sequence length due to the global attention layers inside these models. This limits both their scalability and efficiency. In this work, we address this challenge with a simple yet general strategy: restricting the number of key/value tokens that each query interacts with during global attention. To achieve effective token selection, we introduce a two-stage framework. First, an inter-frame selection step operates at the frame level to identify frames that should be preserved. Second, an intra-frame selection step further discards more redundant tokens within the selected frames. Our analysis highlights the advantage of a diversity-based strategy for inter-frame selection, which ensures broad coverage of the scene. For intra-frame selection, we show that layer-aware sparsification is necessary, with the selection process guided by the entropy of the global attention pattern. Our approach offers a superior speed-accuracy trade-off compared to existing solutions. Extensive experiments show that it accelerates visual geometry transformers by over 85% for scenes with 500 images while maintaining, or even improving, baseline performance, which hints that how our token selection strategy can play a crucial role in future applications of visual geometry transformers. Our project website is available at https://zsh2000.github.io/good-token-hunting.github.io.

Recent Open-Vocabulary Action Recognition (OVAR) methods typically aggregate visual features into a global representation before computing text alignment, a process that obscures local patch information and fine-grained spatio-temporal cues. We propose Similarity Volume Aggregation (SimVA), a framework that constructs a dense 4D spatio-temporal similarity volume from patch-level visual-text similarities. SimVA constructs a spatio-temporal similarity volume over local video tokens and action classes, and employs class sampling to ensure similarity aggregation scalable to large vocabularies. The similarity volume is refined by spatial aggregation, which contextualizes local similarity patterns to improve intra-frame consistency. Motion-aware modulation further injects inter-frame variation cues, highlighting dynamically changing regions. Mamba-based temporal aggregation then models the evolution of class-conditioned similarity patterns across frames. By maintaining dense visual-text correspondence, SimVA effectively transfers CLIP to video action recognition, achieving competitive performance across zero-shot, few-shot, and base-to-novel benchmarks.

Image-to-video models often generate videos that remain overly static, compared to text-to-video models. While prior approaches mitigate this issue by weakening or modifying the image-conditioning signal, they often require additional training or sacrifice fidelity to the reference image. In this work, we identify reference-frame dominance as a key mechanism behind motion suppression. We observe that non-reference frames in I2V models allocate excessive self-attention to reference-frame key tokens, causing reference information to be over-propagated across time and suppressing inter-frame dynamics. Based on this finding, we propose DyMoS (Dynamic Motion Slider), a training-free and model-agnostic method that rebalances the attention pathway from generated frames to the reference frame during initial denoising steps. DyMoS leaves both the input image and model weights unchanged and introduces a single scalar parameter for continuous control over motion strength. Experiments across multiple state-of-the-art I2V backbones demonstrate that DyMoS consistently improves motion dynamics while maintaining visual quality and fidelity to the reference image.

Video outpainting generates plausible visual content beyond the original spatial extent of a video, playing a key role in adapting videos to diverse display formats. To support such use cases, it must enable large spatial extrapolation over long sequences. However, most existing methods address only one of these challenges or lack explicit mechanisms for ensuring global spatio-temporal consistency, leading to notable limitations. In this paper, we propose HL-OutPaint, a high-resolution video outpainting framework for long sequences. Our approach follows a coarse-to-fine strategy with a two-stage pipeline. We first construct Global Coarse Guidance (GCG), a low-resolution representation that captures global structure and dominant motion across the video. Unlike naive downsampling, GCG is built via a novel global-local frame swapping mechanism that couples sparse global keyframes with local temporal windows and exchanges information during sampling. This enables GCG to encode both long-term structural consistency and short-term temporal dynamics in a unified representation. Guided by this representation, HL-OutPaint then performs high-resolution outpainting to generate spatially detailed and temporally consistent content. By separating global structure modeling from fine-grained synthesis, our framework achieves stable, coherent generation for large spatial expansion and long video sequences. Extensive experiments show that HL-OutPaint outperforms existing methods in challenging scenarios involving wide spatial extrapolation and long video sequences.

Streaming 3D reconstruction under a strict constant-memory budget hinges on how the recurrent state is updated as the stream evolves. We profile TTT3R-style per-token gates across five benchmarks and discover a structural bottleneck: the gate is intrinsically bounded in magnitude (median $0.31$; never exceeding $0.6$) and nearly frame-invariant, yielding an effective memory horizon of only $\sim$3 frames per state token, which serves as the structural origin of long-sequence drift. We trace this to a missing axis: existing inference-time methods modulate updates only at the per-token, intra-frame level, while the orthogonal frame-level question of \emph{how strongly each frame should contribute to the state} has been treated as content-independent. We close this gap with a scalar frame-level gate $α_t \in (0, 1]$ derived in closed form from frame-to-frame changes of internal features -- a continuous relaxation of classical Simultaneous Localization and Mapping (SLAM) keyframe selection that requires no parameters, no training, and no extra forward pass. Across six benchmarks spanning camera pose, video depth, and 3D reconstruction at sequence lengths up to $4,541$ frames, our gate cuts ATE by $51\%$ on long TUM-RGBD pose sequences, reduces AbsRel by $12.8\%$ on Bonn video depth, and on KITTI long-sequence pose estimation surpasses both LongStream and Keyframe-VO, while retaining strictly constant memory at zero training cost.

Data assimilation (DA) estimates the state of an evolving dynamical system from noisy, partial observations, and is widely used in scientific simulation as well as weather and climate science. In practice, filtering methods rely on frame-to-frame transition models. However, these models are fragile when observations are non-Markovian (when they form only a partial slice of a higher-dimensional latent state as in real-world weather data): they tend to accumulate errors over long horizons. At the same time, learned DA methods typically commit to a single regime, either filtering (nowcasting, real-time forecasting) or smoothing (retrospective reanalysis), which splits what should be a shared prior across application-specific pipelines. To address both issues, we introduce ForcingDAS, a unified and robust DA framework. Built on Diffusion Forcing with an independent noise level assigned to each frame, ForcingDAS learns a joint-trajectory prior instead of frame-to-frame transitions. This allows it to capture long-horizon temporal dependencies and reduce error accumulation. In addition, the same trained model spans the full filtering to smoothing spectrum at inference time. Specifically, nowcasting, fixed-lag smoothing, and batch reanalysis are selected through the inference schedule alone, without retraining. We evaluate ForcingDAS on 2D Navier-Stokes vorticity, precipitation nowcasting, and global atmospheric state estimation. Across all settings, a single model is competitive with or outperforms both learned and classical baselines that are specialized for individual regimes, with the largest gains observed on real-world weather benchmarks.

Video depth estimation extends monocular prediction into the temporal domain to ensure coherence. However, existing methods often suffer from spatial blurring in fine-detail regions and temporal inconsistencies. We argue that current approaches, which primarily rely on temporal smoothing via Transformers, struggle to maintain strict 3D geometric consistency-particularly under rotations or drastic view changes. To address this, we propose GemDepth, a framework built on the insight that an explicit awareness of camera motion and global 3D structure is a prerequisite for 3D consistency. Distinctively, GemDepth introduces a Geometry-Embedding Module (GEM) that predicts inter-frame camera poses to generate implicit geometric embeddings. This injection of motion priors equips the network with intrinsic 3D perception and alignment capabilities. Guided by these geometric cues, our Alternating Spatio-Temporal Transformer (ASTT) captures latent point-level correspondences to simultaneously enhance spatial precision for sharp details and enforce rigorous temporal consistency. Furthermore, GemDepth employs a data-efficient training strategy, effectively bridging the gap between high efficiency and robust geometric consistency. As shown in Fig.2, comprehensive evaluations demonstrate that GemDepth achieves state-of-the-art performance across multiple datasets, particularly in complex dynamic scenarios. The code is publicly available at: https://github.com/Yuecheng919/GemDepth.

Multi-Object Tracking (MOT) in dynamic environments relies on robust temporal reasoning to maintain consistent object identities over time. Transformer-based end-to-end MOT models achieve strong performance by explicitly modeling temporal dependencies, yet training them requires extensive bounding-box and identity annotations. Given the high labeling cost and strong redundancy in videos, Active Learning (AL) is an effective approach to improve annotation efficiency. However, existing AL methods for MOT primarily operate at the frame level, which is structurally misaligned with modern end-to-end trackers whose inference and training rely on multi-frame clips. To bridge this gap, we formulate clip-level active learning and propose Clip-level Uncertainty and Temporal-aware Active Learning (CUTAL). In contrast to frame-based approaches, CUTAL scores each clip using uncertainty metrics derived from multi-frame predictions to capture inter-frame correspondence ambiguities, while enforcing temporal diversity to select an informative and non-redundant subset. Experiments show that CUTAL achieves stronger overall performance than baselines at the same label budgets across MeMOTR and SambaMOTR. Notably, CUTAL achieves performance comparable to full supervision for MeMOTR on both datasets using only 50% of the labeled training data.

Tracking points in videos is typically formulated as frame-to-frame correspondence, where each point is matched locally to the next frame. While this works over short horizons, errors accumulate under articulation, occlusion, and viewpoint change, leading to silent semantic drift that existing trackers cannot detect or correct. In this work, we revisit long-horizon tracking from a monitoring perspective and introduce QueST, a monitoring-by-design framework that treats interaction-relevant entities as persistent semantic queries rather than transient point tracks. Instead of local propagation, each query attends globally over spatio-temporal video features at every time-step, providing a stable semantic anchor across time. We further constrain query trajectories with lightweight 3D physical grounding, using geometric plausibility to suppress unbounded drift under occlusion. We evaluate QueST on long-horizon articulated sequences from PartNet-Mobility in SAPIEN and compare against RAFT-3D, CoTracker, and TAP-Net. QueST substantially reduces terminal drift achieving a 67.7% Absolute Point Error (APE) improvement over TAP-Net while better preserving identity over extended horizons. Our results show that embedding semantic monitoring directly into perception enables more reliable long-horizon tracking under distribution shift.

Recent advancements in image animation have utilized diffusion models to breathe life into static images. However, existing controllable frameworks typically rely on Lagrangian motion guidance, where optical flow is estimated relative to the initial frame. This paper revisits the same optical-flow primitive through a more local supervision design: we use adjacent-frame Eulerian motion fields to guide generation, where the motion signal always describes a short temporal hop. This shift enables parallelized training and provides bounded-error supervision throughout the generation process. To mitigate the drift artifacts common in adjacent frame generation, we introduce a Bidirectional Geometric Consistency mechanism, which computes a forward-backward cycle check to mathematically identify and mask occluded regions, preventing the model from learning incorrect warping objectives. Extensive experiments demonstrate that our approach accelerates training, preserves temporal coherence, and reduces dynamic artifacts compared to reference-based baselines. The code, model, and data have been made available at https://nguyentthong.github.io/eulerian/

The de facto approach in video object-centric learning maintains temporal consistency through learned dynamics modules that predict future object representations, called slots. We demonstrate that these predictors function as expensive approximations of discrete correspondence problems. Modern self-supervised vision backbones already encode instance-discriminative features that distinguish objects reliably. Exploiting these features eliminates the need for learned temporal prediction. We introduce Grounded Correspondence, a framework that replaces learned transition functions with deterministic bipartite matching. Slots initialize from salient regions in frozen backbone features. Frame-to-frame identity is maintained through Hungarian matching on slot representations. The approach requires zero learnable parameters for temporal modeling yet achieves competitive performance on MOVi-D, MOVi-E, and YouTube-VIS. Project page: https://magenta-sherbet-85b101.netlify.app/

Artificial satellites and space debris increasingly contaminate astronomical images, affecting scientific surveys and producing large volumes of streaked exposures. Manual inspection is no longer feasible at scale, and reliable detection and characterisation of streaks has become essential for both data-quality control and the monitoring of objects in Earth orbit. We present StreakMind, an automated pipeline designed to detect Near-Earth Objects and satellite streaks in astronomical images, characterise their geometry, and cross-identify them with known orbital objects. The system integrates all inference results into a structured database suitable for large surveys. A YOLO OBB model was trained on a hybrid dataset of 2335 images and applied to processed FITS frames. Geometric refinement, inter-frame association, satellite cross-identification, and Gaussian-based confidence scoring were then used to produce final identifications stored in a relational database. Observations from La Sagra Observatory were used to develop and test the method. On the test set, the model achieved a precision of 94 percent and a recall of 97 percent. It reliably detected faint streaks, delivered consistent geometric reconstructions, and performed robust satellite cross-identification. StreakMind demonstrates strong potential for large-scale automated analysis of linear streaks produced by both Near-Earth Objects and artificial satellites, contributing to space situational awareness.

Video snapshot compressive imaging (SCI) enables the reconstruction of dynamic scenes from a single snapshot measurement. Recently, NeRF-based methods have shown promising reconstruction performance. However, such methods typically adopt random ray sampling strategies and fail to capture content structural similarities, resulting in limited reconstruction quality. To address these issues, we first propose a patch-level ray sampling strategy to enable the modeling of content structure. Then, we propose an Inter- and Intra-Ray Transformer (RayFormer) to capture the structural similarities, modeling both inter-ray similarities among spatially neighboring points at the same depth and intra-ray correlations between adjacent points along the viewing ray. Finally, benefiting from the patch-level sampling strategy, the total variation prior is incorporated into the objective function to enhance spatial smoothness and suppress artifacts. Experiments in both simulated and real-world scenes demonstrate that the proposed method achieves state-of-the-art (SOTA) reconstruction performance.

Avatar fingerprinting, i.e., verifying who drives a synthetic talking-head video rather than whether it is real, is a critical safeguard for authorized use of face-reenactment technology. Existing methods rely on a fixed, non-differentiable landmark extraction stage that prevents the fingerprinting model from being optimized end-to-end from raw pixels. We propose a preprocessing-free system built on a micro-expression-aware backbone operating on raw video frames, with inter-frame feature differencing as the core design principle: consecutive feature maps are subtracted in the learned deep feature space, so that temporally stable appearance dimensions contribute zero to the output while driver-specific motion dynamics are preserved. A controlled ablation on NVFAIR confirms that temporal motion accounts for the large majority of discriminative performance, and that raw appearance features actively degrade identity separation. Both the choice of backbone and the differencing principle are essential: differencing alone is insufficient when applied to a generic encoder, as appearance-dominated features collapse to near-identical representations across adjacent frames, while the micro-expression-aware F5C backbone retains measurable motion variation that the differencing operation can exploit. Without any external preprocessing, our model achieves an overall AUC of 0.877 on NVFAIR and matches or exceeds the landmark-based baseline on the majority of cross-generator pairs.

Video outpainting aims to expand the visible content of a video beyond the original frame boundaries while preserving spatial fidelity and temporal coherence across frames. Existing methods primarily rely on large-scale generative models, such as diffusion models. However, generationbased approaches suffer from implicit temporal modeling and limited spatial context. These limitations lead to intraframe and inter-frame inconsistencies, which become particularly pronounced in dynamic scenes and large outpainting scenarios. To overcome these challenges, we propose Seen-to-Scene, a novel framework that unifies propagationbased and generation-based paradigms for video outpainting. Specifically, Seen-to-Scene leverages flow-based propagation with a flow completion network pre-trained for video inpainting, which is fine-tuned in an end-to-end manner to bridge the domain gap and reconstruct coherent motion fields. To further improve the efficiency and reliability of propagation, we introduce a reference-guided latent propagation that effectively propagates source content across frames. Extensive experiments demonstrate that our method achieves superior temporal coherence and visual realism with efficient inference, surpassing even prior state-of-the-art methods that require input-specific adaptation.

Exo-to-Ego video generation aims to synthesize a first-person video from a synchronized third-person view and corresponding camera poses. While paired supervision is available, synchronized exo-ego data inherently introduces substantial spatio-temporal and geometric discontinuities, violating the smooth-motion assumptions of standard video generation benchmarks. We identify this synchronization-induced jump as the central challenge and propose Syn2Seq-Forcing, a sequential formulation that interpolates between the source and target videos to form a single continuous signal. By reframing Exo2Ego as sequential signal modeling rather than a conventional condition-output task, our approach enables diffusion-based sequence models, e.g. Diffusion Forcing Transformers (DFoT), to capture coherent transitions across frames more effectively. Empirically, we show that interpolating only the videos, without performing pose interpolation already produces significant improvements, emphasizing that the dominant difficulty arises from spatio-temporal discontinuities. Beyond immediate performance gains, this formulation establishes a general and flexible framework capable of unifying both Exo2Ego and Ego2Exo generation within a single continuous sequence model, providing a principled foundation for future research in cross-view video synthesis.

3D Gaussian Splatting (3DGS) enables real-time, photorealistic novel view synthesis, making it a highly attractive representation for model-based video tracking. However, leveraging the differentiability of the 3DGS renderer "in the wild" remains notoriously fragile. A fundamental bottleneck lies in the compact, local support of the Gaussian primitives. Standard photometric objectives implicitly rely on spatial overlap; if severe camera misalignment places the rendered object outside the target's local footprint, gradients strictly vanish, leaving the optimizer stranded. We introduce SpectralSplats, a robust tracking framework that resolves this "vanishing gradient" problem by shifting the optimization objective from the spatial to the frequency domain. By supervising the rendered image via a set of global complex sinusoidal features (Spectral Moments), we construct a global basin of attraction, ensuring that a valid, directional gradient toward the target exists across the entire image domain, even when pixel overlap is completely nonexistent. To harness this global basin without introducing periodic local minima associated with high frequencies, we derive a principled Frequency Annealing schedule from first principles, gracefully transitioning the optimizer from global convexity to precise spatial alignment. We demonstrate that SpectralSplats acts as a seamless, drop-in replacement for spatial losses across diverse deformation parameterizations (from MLPs to sparse control points), successfully recovering complex deformations even from severely misaligned initializations where standard appearance-based tracking catastrophically fails.

Event cameras excel at high-speed, low-power, and high-dynamic-range scene perception. However, as they fundamentally record only relative intensity changes rather than absolute intensity, the resulting data streams suffer from a significant loss of spatial information and static texture details. In this paper, we address this limitation by leveraging the generative prior of a pre-trained video diffusion model to reconstruct high-fidelity video frames from sparse event data. Specifically, we first establish a baseline model by directly applying event data as a condition to synthesize videos. Then, based on the physical correlation between the event stream and video frames, we further introduce the event-based inter-frame residual guidance to enhance the accuracy of video frame reconstruction. Furthermore, we extend our method to video frame interpolation and prediction in a zero-shot manner by modulating the reverse diffusion sampling process, thereby creating a unified event-to-frame reconstruction framework. Experimental results on real-world and synthetic datasets demonstrate that our method outperforms previous reconstruction approaches on most quantitative metrics and achieves superior qualitative results, while achieving competitive zero-shot performance compared with dedicated methods explicitly trained for interpolation and prediction tasks. We also refer the reviewers to the video demo contained in the supplementary material for video results. The code will be publicly available at https://github.com/CS-GangXu/UniE2F.

Tissue deformation recovery based on stereo endoscopic images is crucial for tool-tissue interaction analysis and benefits surgical navigation and autonomous soft tissue manipulation. Previous research suffers from the problems raised from camera motion, occlusion, large tissue deformation, lack of tissue-specific biomechanical priors, and reliance on offline processing. Unlike previous studies where the tissue geometry and deformation are represented by 3D points and displacements, the proposed method models tissue geometry as the 3D point and derivative map and tissue deformation as the 3D displacement and local deformation map. For a single surface point, 6 parameters are used to describe its rigid motion and 3 parameters for its local deformation. The method is formulated under the camera-centric setting, where all motions are regarded as the scene motion with respect to the camera. Inter-frame alignment is realized by optimizing the inter-frame deformation, making it unnecessary to estimate camera pose. The concept of the canonical map is introduced to optimize tissue geometry and deformation in an online approach. Quantitative and qualitative experiments were conducted using in vivo and ex vivo laparoscopic datasets. With the inputs of depth and optical flow, the method stably models tissue geometry and deformation even when the tissue is partially occluded or moving outside the field of view. Results show that the 3D reconstruction accuracy in the non-occluded and occluded areas reaches 0.37$\pm$0.27 mm and 0.39$\pm$0.21 mm in terms of surface distance, respectively. The method can also estimate surface strain distribution during various manipulations as an extra modality for mechanical-based analysis.

Head swapping replaces an entire head while preserving pose, expression, body motion, and scene. Progress is limited by the lack of cross-identity paired videos: real footage cannot provide different identities performing exactly the same motion, leaving the task without paired supervision or frame-aligned ground truth. Existing methods therefore rely on same-identity masked reconstruction, which restricts supervision to predefined editable regions. To address this, we introduce an identity-expression decoupled synthesis pipeline that constructs expression-synchronized cross-identity video pairs from real footage. Expression-bearing facial regions are retained under small clip-consistent geometric perturbations, while the surrounding head is regenerated with a new identity as synthesized swapping input. These pairs form a cross-identity benchmark with frame-aligned real-world video as ground-truth targets, enabling full-reference evaluation of identity, expression, pose, reconstruction fidelity, and temporal stability. This yields HeadSwapBench, the first cross-identity paired dataset for video head swapping, supporting both training (20,278 videos) and benchmarking (1,040 videos). With the cross-identity supervision enabled by this paired dataset, we propose DirectSwap, a mask-free video head swapping training paradigm. Under otherwise identical settings, this formulation outperforms head- and rectangle-masked same-identity reconstruction, particularly for bidirectional head-silhouette changes. At inference, driving-output divergence and emergent reference attention estimate the edit support, allowing unchanged non-head content to be restored from the driving video without external segmentation or additional training. On 1,040 clips from 104 unseen subjects, the resulting model demonstrates that the proposed paired supervision supports effective whole-head swapping.