Overview

Vision foundation models learn reusable visual representations from large image or video collections, often through self-supervised methods such as contrastive learning, masked prediction, and feature prediction, or through image-text and generative training. Researchers adapt them using frozen-feature probes, prompts, lightweight fine-tuning, distillation, and feature fusion for tasks ranging from classification and segmentation to depth, 3D geometry, and video understanding. These methods can transfer across tasks and domains, but specialized pretraining or adaptation can still be important in settings such as medical imaging, remote sensing, and scientific vision. A central open tension is whether broad pretrained representations can provide reliable spatial, temporal, and domain-robust understanding while remaining efficient and consistently evaluated.

Latest papers

152 papers16 papers in the last four weeks, up 7% on the four weeks before. 0.1% of all new papers.

Jul 25, 2026

A Scale-adaptive Vision Model Links C. elegans Neuronal Morphology to Behavior for Neurotoxicity Assessment

Neurological disorders are a leading cause of global disability and are increasingly linked to environmental chemical exposures. Yet neurotoxicity assessment still relies on hand-scored morphological readouts that are subjective and poorly predictive of behavioral outcomes. Caenorhabditis elegans provides a genetically tractable, 3R-compliant alternative, but quantifying neuronal phenotypes from confocal microscopy at scale remains computationally challenging: existing vision foundation models, trained on natural or radiological images, cannot resolve the sparse signals and multi-scale lesions of neuronal imaging. Here, we introduce a dedicated self-supervised vision model for C. elegans dopaminergic neurons, together with CeNeuMorph, a multi-grained confocal benchmark of 27,117 annotated images. Specifically, moving beyond standard Masked Autoencoders, we propose a scale-adaptive masked image modeling strategy that jointly learns representations across resolutions and patch sizes under a fixed token budget. By decoupling structural semantic learning from rigid grid constraints, the model effectively resolves the full spectrum of neurodegenerative lesions - ranging from fine dendritic beading to gross soma shrinkage - within a tractable computational framework. Finally, our model surpasses both generalist and biomedical foundation models across classification, segmentation and detection tasks. Fusing visual features with morphological descriptors enables prediction of dopamine-dependent behavioral deficits (R2=0.498R^2=0.498). Screening 180 agrochemicals, we identify the benzimidazole moiety as a previously unrecognized determinant of dopaminergic neurotoxicity. Together, the work demonstrates how scale-adaptive self-supervised learning can connect morphology to function for a scalable alternative to mammalian in vivo models for neurotoxicity assessment and drug discovery.
Jul 24, 2026

Rethinking Multi-Branch and Cross-Backbone Fusion for Vehicle Re-Identification under Foundation-Model Pretraining

Multi-branch architectures and CNN-Transformer fusion are widely believed to improve vehicle re-identification (Re-ID) by combining complementary representations. We revisit this for a DINOv3-pretrained backbone. A single DINOv3-pretrained ConvNeXt with a tuned recipe reaches 88.19 mAP on VeRi-Wild Small and 77.47 on Large from visual cues alone, within the combined evaluation and optimization noise of the strongest protocol-verified metadata-dependent multi-branch baseline, and 92.38/83.68 with training-free re-ranking. Using this baseline and retrieval-level branch diagnostics, we ask whether representational diversity still pays at this scale. In our runs, it does not. Across both benchmarks and every converged configuration, concatenating multiple heads over a shared backbone moves the best single head by under one mAP point in either direction while costing four times the embedding dimension; 99.7% of the concatenation's variance lies in 512 principal components, so the heads not only duplicate one another but each occupies a quarter of its nominal 2048 dimensions. Pushing diversity to its architectural limit, CNN versus Transformer, we grant fusion every advantage through an asymmetric frozen-anchor scheme. Every Transformer configuration still lands at least 13 mAP below the ConvNeXt backbone (13-15 for the two strongest, up to 46 for the weakest), and a paired per-query bootstrap bounds the fusion gain at +0.11 mAP (95% CI) even for the most favourable snapshot we obtained. One strong backbone with the right recipe and re-ranking is the efficiency frontier. All results use single-seed training and one foundation-model family; differences of this size are therefore reported as bounds rather than orderings, and we list falsifiers.
Jul 17, 2026

Do Vision Encoders Exhibit Human-like Color Thresholds?

Understanding and characterizing human color perception is a longstanding research goal. One of the most traditional approaches is looking for the human color discrimination thresholds, the minimum chromatic differences perceptible to human observers. In recent years, deep neural networks have become the standard networks for computer vision tasks. In particular, deep vision encoders, foundation models trained on large-scale visual data, map images into latent feature representations. Despite the widespread use of deep vision encoders, few studies have investigated whether their internal representations exhibit human-like discrimination thresholds. In this work, we present a large-scale exploratory study probing the chromatic sensitivity of more than 50 pretrained vision encoders, including convolutional networks and vision transformers, against human discrimination thresholds. Using controlled chromatic stimuli at multiple chroma levels, we compare model-derived chromatic discrimination thresholds with human discrimination ellipses through a region-overlap metric (mIoU). Our analysis reveals generally weak alignment between model representations and human perceptual thresholds across all model families, with the best mIoU < 0.25. Moreover, we find that self-supervised encoders consistently outperform supervised ones, while language-supervised models show the most polarized behavior, occupying both the top and bottom of the ranking. These findings suggest that human-like chromatic sensitivity does not emerge naturally from current large-scale visual training objectives for any of the analyzed architectures.
Jul 16, 2026

Beyond Single Expert: Harmonizing Diverse Visual Priors in MLLMs for Spatial Understanding

Multimodal Large Language Models (MLLMs) have demonstrated substantial promise in spatial understanding. Existing works typically incorporate prior knowledge extracted from a pre-trained foundation model to further enhance the spatial awareness of MLLMs. In this paper, we first reveal that when integrating diverse foundation models into MLLMs, different models provide complementary spatial priors that benefit different tasks. Motivated by this, we propose ViPS\textbf{ViPS}, a novel multi-model prior framework designed to fully unleash the potential of incorporating multiple Vi\textbf{Vi}sual P\textbf{P}riors from diverse models into MLLMs for S\textbf{S}patial understanding. Specifically, ViPS introduces an Efficient Prior Proxy to generate multiple foundational priors with minimal inference overhead, and a Dynamic Prior Fusion mechanism to achieve harmonious and context-aware prior fusion and injection from the prior proxies. Extensive experiments demonstrate that ViPS successfully harmonizes diverse visual priors, establishing new state-of-the-art performance across multiple complex spatial reasoning and 3D spatial understanding benchmarks. Project page: https://visual-ai.github.io/vips
Jul 15, 2026

Emergent Region-Level Facial Correspondence in Frozen Vision Foundation Models

Frozen self-supervised vision models can align parts of generic objects, but it remains unclear whether this correspondence extends to human faces, where global layout is shared while identity-specific appearance varies sharply. We test whether frozen DINOv3 features define a region-level facial coordinate system: a feature space in which eyes, brows, nose, mouth, skin, and hair remain distinguishable across people and across time without face-specific training. Using DINOv3 ViT-L/16 patch embeddings and FaRL only as a face-part labeling interface, we evaluate cross-identity nearest-neighbor matching and temporal label propagation on 200 CelebDF-v2 real videos. DINOv3 achieves 83.0% region-level semantic accuracy under unconstrained cross-identity matching, compared with a 23.0% area-weighted random baseline, and 95.5% temporal tracking accuracy without a learned temporal module. A no-FaRL control collapses to 0.9%, showing that FaRL supplies semantic initialization while DINOv3 supplies dense spatial correspondence. The strongest correspondence appears at an intermediate layer: block 18 gives a 4.93x same-region versus cross-region discrimination ratio, compared with 1.48x at the final block. Against CLIP ViT-L/14, DINOv3 shows only a small aggregate advantage but a +16.8 pp gain on anatomical regions, indicating that image-level contrastive supervision captures coarse facial layout but not fine-grained anatomical identity. These results establish frozen DINOv3 as a strong zero-shot representation for region-level facial correspondence and identify intermediate self-supervised features as the most useful layer for dense face analysis.
Jul 14, 2026

ViCo3D: Empowering LiDAR-based Collaborative 3D Object Detection with Vision Foundation Models

LiDAR-based collaborative 3D perception in Vehicle-to-Everything (V2X) systems typically relies on fusing bird's-eye-view (BEV) features across agents. However, current BEV representations, typically extracted by LiDAR backbones trained from scratch, are geometry-dominated and lack general semantic priors, inherently limiting the efficacy of feature-level collaboration. Meanwhile, vision foundation models (VFMs) pretrained on large-scale image data have demonstrated strong capability in learning general-purpose and informative visual representations for 2D tasks, and have the potential to enhance agent-wise LiDAR BEV representations for collaboration. Despite this potential, adapting VFMs to LiDAR-based 3D detection remains challenging due to the substantial image-point cloud modality gap. To bridge this gap, we propose ViCo3D, a collaborative 3D object detection framework powered by VFMs. Specifically, ViCo3D adapts VFMs to LiDAR-based collaborative perception from three aspects: First, ViCo3D projects point clouds onto the BEV plane as three-channel images, enabling DINOv2 to extract BEV-space visual features from LiDAR inputs. Besides, to effectively integrate these DINOv2-derived features with LiDAR geometric features, ViCo3D introduces a multi-scale BEV fusion module within the single-agent encoder. In addition, ViCo3D adopts an ego-centric cross-agent fusion strategy to aggregate complementary information from multiple agents. Experiments on DAIR-V2X and V2XSet demonstrate that ViCo3D achieves state-of-the-art 3D detection performance. Remarkably, it delivers up to 1.8x greater collaborative gains than prior methods on DAIR-V2X. The code will be made public available for future investigation.
Jul 14, 2026

Let RGB Be the Language of Vision

This work introduces a unified formulation for vision models, where diverse forms of visual information beyond natural images, such as masks, depth maps, and other structured visual signals, are all represented as RGB images, while general visual tasks can be converted into a common RGB-to-RGB image editing problem. In this paradigm, different types of visual information internally share the same encoding and decoding architecture and parameters as natural images, enabling a single model to transfer across tasks through a unified visual interface, in a way analogous to how language models operate over text. We refer to this formulation as RGB In and RGB Out (RINO). Built upon a generic image editing backbone without task-specific fine-tuning, RINO demonstrates robust and competitive zero-shot performance on both dense understanding tasks such as segmentation and depth estimation (where we unify outputs as RGB), and dense-conditioned generation tasks such as pose-to-image generation (where we unify inputs as RGB). We hope this study provides useful insights toward general unified vision-language systems, where diverse visual tasks can be expressed, interpreted, and solved through a shared visual language. Code is available at https://github.com/yangtiming/RINO.
Jul 10, 2026

Video Generation Models are General-Purpose Vision Learners

Driven by next-token prediction, NLP shifted from task-specific models into powerful generalist foundation models. What, then, is the equivalent catalyst needed to achieve a general-purpose model in computer vision? In this paper, we contend that large-scale text-to-video generation serves as a strong pre-training paradigm for computer vision, providing the necessary spatiotemporal priors, vision-language alignment, and scalability required for general visual intelligence. We introduce GenCeption, which leverages a pre-trained video generative diffusion backbone to define a feed-forward perception model, capable of performing various vision tasks steered by text instructions. Empirical results demonstrate that GenCeption achieves state-of-the-art performance across a diverse suite of tasks, including depth, surface normal, and camera pose estimation, expression-referring segmentation, and 3D keypoint prediction, often matching or surpassing specialized models (e.g. DepthAnything3, SAM3, D4RT, VGGT-Omega, Sapiens, David, Genmo, and Lotus-2). Furthermore, the video generative pretrained backbone outperforms alternative pretraining paradigms (e.g., V-JEPA, and Video MAE) under comparable settings. Importantly, GenCeption exhibits preliminary data and model scaling properties along with exceptional data efficiency, where it achieves comparable performance with leading models like D4RT and VGGT-Omega with 7 to 500 less training data. Finally, GenCeption also exhibits intriguing emergent behaviors: a model trained exclusively on synthetic human videos generalizes to real-world footage and out-of-distribution object categories (e.g., animals and robots). These findings suggest that video generation is not merely a synthesis tool, but a foundational path toward generalist vision intelligence for the physical world. Project page: https://genception.github.io
Jul 8, 2026

Vision Foundation Models in Radiology: A Scoping Review of Data, Methodology, Evaluation and Clinical Translation

Vision foundation models (VFMs) are increasingly being developed for radiological imaging, yet their definition, development and evaluation remain heterogeneous. We conducted a PRISMAScR scoping review of peer-reviewed studies published between January 2017 and March 2026 describing foundation models trained exclusively on radiological imaging data. Sixty-seven studies were included and mapped across three pillars: data scale and heterogeneity, architectural and pretraining scalability, and downstream transferability and generalization. Datasets primarily covered brain MRI, thoracoabdominal CT, and chest X-ray, ranging from fewer than 100,000 samples to multi-million-image cohorts. Transformer-based architectures and self-supervised pretraining predominated, particularly masked image modeling, contrastive learning and multi-stage approaches. Evaluation focused mainly on segmentation and classification, whereas cross-center, cross-scanner, anatomical and modality-shift validation was inconsistently reported. Alignment with FUTURE-AI principles was uneven. Overall, radiology-specific VFMs show promising transferability, but clinical translation remains constrained by limited data representativeness, heterogeneous benchmarks, incomplete reporting and insufficient deployment-oriented evaluation.
Jul 2, 2026

RayTun3R: Online Camera Adaptation in 3D Foundation Models

Recent 3D foundation models, such as DUSt3R, MASt3R, VGGT, π3π^3, and Depth Anything 3, provide strong feed-forward depth and pose estimates on pinhole imagery, but degrade sharply under fisheye camera geometry. We show that this failure is partly caused by a pinhole camera bias in the positional encodings of pretrained 3D foundation models, and propose RayTun3R, a lightweight camera adaptation approach. It keeps the pretrained network fixed and adapts only lightweight components tied to token position and camera geometry. RayTun3R learns parameter-efficient residual corrections to absolute and rotary positional encodings, together with parameter-free tokenization and corrections to prediction-grid coordinates that remove residual pinhole assumptions. The resulting adapter contains only 10,752 trainable parameters and can be learned from a short temporal segment using geometric losses. Once adapted, RayTun3R transfers effectively to the remaining frames of the sequence without incurring additional runtime costs. Across diverse fisheye datasets with fields of view from 110∘110^\circ to 200∘200^\circ, our adapter reduces rotation error by 22-12×12\times relative to the unadapted model, outperforms LoRA while using ∼ ⁣14×\sim\!14\times fewer trainable parameters, improves pose over adaptation-free baselines while avoiding their multi-view inference cost, and remains competitive on depth accuracy.
Jun 30, 2026

MuSViT: A Foundation Vision Model for Sheet Music Representation

Foundation models have transformed vision and language processing by providing rich, reusable representations that transfer across diverse tasks. Sheet music, as a visual encoding of musical language, lacks such a strong domain-specific backbone. We introduce MuSViT (Music Score Vision Transformer): the first foundation vision model for sheet music representation -- a ViT encoder pre-trained via Masked Autoencoders on 9.7 million pages from the IMSLP. To handle the complexity of real-world scores, we adopt a two-stage curriculum: a synthetic warm-up on typeset scores followed by large-scale training on the full IMSLP corpus. We evaluate MuSViT on four downstream tasks -- full-page and staff-level music score recognition, music symbol detection, and score difficulty classification -- under two scenarios: linear probing (frozen encoder) and fine-tuning. Under linear probing, MuSViT consistently outperforms modern vision encoders, revealing that general-purpose representations, regardless of scale, fall systematically short on the structured symbolic properties of musical notation. Under fine-tuning, MuSViT generally improves upon task-specific state-of-the-art methods. An additional embedding-transcription consistency analysis reveals that MuSViT encodes symbolic musical structure directly in its representation space -- unlike other encoders, whose embeddings do not correlate with music notation content. These results establish MuSViT as a foundation backbone for sheet music understanding.
Jun 26, 2026

Panoramic Scene Understanding: A Survey from Distortion-Aware Engineering to Sphere-Native Modeling

Panoramic images capture the full visual sphere in a frame, offering context unavailable to conventional cameras. Yet this completeness has an unavoidable geometric cost: the 2-sphere cannot be faithfully mapped to the plane, and every projection introduces distortions that challenge standard vision architectures. This survey traces panoramic scene understanding from projection-based adaptation and distortion-aware engineering to sphere-native modeling, reflecting increasing commitment to spherical geometry. Foundation models form a fourth family, geometry-aware tokenization, which adapts the input interface while reusing perspective-pretrained weights. We review these approaches across five task families: dense prediction, unified multi-task understanding, open-world perception, vision-language reasoning, and dynamic video analysis. Across tasks, the same shift toward spherical geometry recurs. In practice, however, the field has converged not on the strongest sphere-native operators, which are exactly rotation-equivariant but cannot reuse perspective-pretrained backbones and thus have not scaled, but on a compatibility-preserving middle ground combining moderate geometric awareness with large pretrained models. This commitment is uneven: deepest in dense prediction and shallowest in dynamic perception, where methods are spatially sphere-aware yet temporally planar. Foundation-model adaptation has advanced panoramic depth fastest, while layout, surface-normal, and video-level understanding remain largely unexplored. No panoramic foundation model has yet been pretrained on spherical data. We identify five evaluation gaps: spherical-area-weighted metrics, seam-consistency tests, polar-robustness stratification, cross-projection generalization, and standardized open-world protocols. We conclude with a six-point roadmap toward general-purpose panoramic intelligence.
Jun 23, 2026

TuringViT: Making SOTA Vision Transformers Accessible to All

Modern VLMs and VLA systems commonly adopt off-the-shelf ViTs such as SigLIP2 as visual encoders, but diverse downstream requirements in latency, temporal modeling, and VLM integration often call for customized SOTA-level ViTs. Training such encoders remains beyond the reach of much of the community, as it requires massive image-text data, while standard softmax attention makes high-resolution or dynamic-resolution pretraining prohibitively costly and often forces low-resolution pretraining followed by post-hoc adaptation. TuringViT addresses these challenges with three key designs: Turing Linear Attention (TLA) for efficient sequence modeling, VISTA-Curation to construct supervision-rich image-video training data, and native dynamic-resolution pretraining that supports flexible inputs from the start and transfers seamlessly to downstream VLMs. As a result, TuringViT outperforms leading open-source ViT baselines with only 10% of the data, achieves stronger downstream VLM performance, and delivers substantially better latency scaling on high-resolution inputs. Our scaling-law analysis further shows that TuringViT continues to improve predictably with curated data scale, far from saturation. Its fast adaptation, hardware-friendly design, and efficient deployment have made it a unified visual foundation across XPeng's AI systems. More broadly, TuringViT provides a reproducible pipeline that dramatically lowers the cost for the community to train, customize, and deploy SOTA-level ViTs, moving toward making such Vision Transformers accessible to all.
Jun 22, 2026

Fursee: Hybrid YOLO-DINOv3 Framework for Fursuit Identity Retrieval and Clustering

Global furry conventions produce massive fursuit photographs, while manual sorting brings heavy labor costs and calls for automatic identity retrieval and clustering solutions. General multimodal models lack dedicated optimization for complex fursuit scenes, and no public benchmark dataset exists for this task. To fill this gap, we build a specialized fursuit image dataset and present a three-stage hybrid pipeline Fursee for fursuit identity retrieval and clustering. First, YOLO detects and crops high-resolution fursuit head patches to improve localization of small and overlapping targets. Second, ArcFace optimizes DINOv3 embeddings to enlarge angular separation between different identities on the feature hypersphere. Third, DBSCAN performs unsupervised clustering, with silhouette-coefficient-driven search automatically selecting optimal hyperparameters rather than fixed manual radius. Retrieval and clustering experiments verify that our pipeline outperforms mainstream multimodal models including GPT5.5, Claude Opus 4.8 and Qwen3.7-Plus on all evaluation metrics, achieving competitive performance for fursuit head retrieval and grouping.
Jun 18, 2026

SAM3 Self-Distillation for Fine-Grained GOOSE 2D Semantic Segmentation

We describe our 4th-place entry to the ICRA 2026 GOOSE 2D Fine-Grained Semantic Segmentation Challenge, which reached a composite mean Intersection-over-Union (mIoU) of 69.73% on the official 1,815-image test set. Our model adapts the image encoder of a recent visual foundation model, Segment Anything Model 3 (SAM3), with a lightweight decoder. Beyond this, we contribute two techniques and one empirical finding: (i) a self-distillation scheme that re-uses SAM3 itself, prompted with ground-truth boxes, as a teacher on the classes where it outperforms our own model; (ii) an image-level multi-scale test-time augmentation scheme that restores multi-scale inference for a fixed-input-size model by rescaling the image rather than the model input; and (iii) the finding that an aggressive photometric distortion from a winning 2025 GOOSE 2D entry, transplanted onto our pipeline, is its single largest source of improvement.
Jun 15, 2026

VISTA: Scale-Aware Visual Navigation via Action History Conditioning

Vision Navigation Foundation Models (VNMs) promise end-to-end learned navigation policies capable of zero-shot deployment across diverse embodiments and environments. To maintain generality, many vision-based navigation models predict normalized actions. However, this normalization introduces a critical deployment vulnerability: applying different scaling factors to the same normalized trajectory alters its physical geometry, which degrades navigation performance and increases collision risks. We address this vulnerability by conditioning the model on normalized action histories alongside image observations, providing explicit context on the relationship between the model's predictions and the robot's actual physical displacement. Furthermore, current VNMs often struggle in visually repetitive environments that lack distinct features. To resolve this issue, we integrate a DINOv3 encoder, whose richer representations enable our model to capture both spatial and geometric dimensions between observations. VISTA generalizes robustly to out-of-distribution environments, achieving 100% goal prediction accuracy in zero-shot, real-world deployment in Outdoor, Forest and Office settings, and an average of 95% checkpoints crossed, demonstrating consistent path following in unseen environments.
Jun 10, 2026

SheafStain: Sheaf-Theoretic Schrödinger Bridge for Spatially and Biologically Coherent Virtual Staining

Current virtual staining approaches offer the potential for time- and cost-efficient biomarker quantification in cancer diagnostics and prognostics. However, patch-wise inference for gigapixel whole-slide images fails to maintain spatial continuity, yielding artifacts that cause catastrophic mismatches with ground-truth images. Although pathology Vision Foundation Models (VFMs) offer rich representations, their self-attention causes varying global contexts to produce inconsistent embeddings for the same physical region. We formalize and validate this "context contamination" as a sheaf-theoretic problem where these embeddings form a presheaf whose sections disagree on overlaps, so no global section restricts to them. To address this, we propose SheafStain, a new approach that reinterprets VFM features as sheaf-like sections for spatially and biologically coherent virtual staining. Specifically, SheafStain integrates class and patch tokens into a Schrödinger Bridge framework as sheaf-like sections. While the class token anchors biological consistency, patch tokens form a per-position spatial map. A feature space from a single VFM encoder pretrained on Hematoxylin & Eosin and Immunohistochemistry supervises both input conditioning and output stain alignment. Departing from prior work that evaluates on isolated 256×256256 \times 256 patches and either random-crops or resizes the 1024×10241024 \times 1024 ground truth, we translate at 256×256256 \times 256 and evaluate on the stitched 1024×10241024 \times 1024 outputs across HER2, ER, PR, and Ki-67. SheafStain demonstrates promising results against six prior methods while mitigating patch-boundary stitching artifacts. Code is available at https://github.com/deepnoid-ai/SheafStain.
Jun 8, 2026

How Do Video Foundation Models Encode Intuitive Physics? Probing Across Pretraining Paradigms

Do video foundation models encode a usable sense of how the physical world works, and does intuitive physics emerge naturally from large-scale video pretraining? In this work, we study whether pretrained video foundation models encode intuitive-physics information in their frozen representations, and how its accessibility varies across pretraining paradigms, layers, backbone variants, and probe types. Using frozen-feature probing on IntPhys2 and Minimal Video Pairs (MVP), we compare predictive joint-embedding models (V-JEPA), masked reconstruction models (VideoMAE), and diffusion-based video generators (LTX-Video). We find that across linear, MLP, and temporal attentive probes, physics-relevant information is generally weakest in early layers and most accessible at intermediate to late depth. On MVP, temporal attentive probes substantially outperform linear readouts, with V-JEPA achieving 95.0% pair consistency. On IntPhys2, linear probes recover more signal, and VideoMAE attains the strongest temporal attentive result at 73.9% violation-of-expectation accuracy. On both benchmarks, attentive probe performance on LTX consistently underperforms compared to the other two pretraining paradigms. Together, these results suggest that intuitive-physics is broadly decodable from video foundation models, but it is not represented as a single, uniform capability. Its accessibility, and especially its temporal grounding, depends much more on the benchmark and readout than on a simple hierarchy of pretraining objectives or model scale.
Jun 7, 2026

Where Does Texture Evidence Live in SAM? Features, Proposal Masks, and Texture Segmentation

Texture segmentation stresses foundation segmentation because meaningful regions are defined by material or repeated appearance rather than object identity. Segment Anything Models (SAMs) often fail by default on such texture-defined partitions, but this failure is ambiguous: the texture evidence may be absent, missing from the proposal bank, or present but selected or assembled incorrectly by an object-centric readout. We ask what texture-relevant evidence is already preserved in frozen SAM before adaptation. We study two frozen evidence spaces: multiscale features, probed with a minimal clustering readout, and the automatic proposal bank, treated as evidence for a supervised consolidation readout. SAM is frozen throughout; we do not fine-tune the backbone or retrain the proposal generator. Across RWTD, STLD, an ADE20K-selected refined-crop complement, and a ControlNet-stitched PTD bridge archive, frozen SAM is not a texture segmenter by default, but its failures are not simple texture blindness. Coarse frozen features preserve texture organization, and proposal banks often contain texture-aligned masks or fragments. Natural scenes more often require assembly and commitment over fragments, while cleaner synthetic cases more often reduce to selecting an already coherent proposal. Default mask failure should therefore be decomposed into representation evidence, proposal-bank support, readout mismatch, and commitment failure.
Jun 2, 2026

PRISM: Synergizing Vision Foundation Models via Self-organized Expert Specialization

Unifying the complementary strengths of diverse Vision Foundation Models (VFMs) into a single efficient model is highly desirable but challenged by the negative transfer inherent in monolithic distillation. To address these feature conflicts, we introduce PRISM, a novel dual-stream Mixture-of-Experts (MoE) framework that synergizes VFMs via modular specialization. We propose a two-stage paradigm: (1) expertise deconstruction, where a teacher-conditional router guides experts to specialize in distinct representational subspaces to mitigate interference, followed by (2) dynamic recomposition, where the router learns to assemble these experts into tailored computational pathways for downstream tasks. Experiments on PASCAL-Context and NYUD-v2 show that PRISM establishes a new state of the art, validating that sparse, emergent specialization is a scalable approach for integrating diverse visual knowledge.
May 30, 2026

Scaling Parallel Sequence Models to Foundation-Scale Vision Encoders

Vision foundation models are bottlenecked by the quadratic cost of self-attention, which limits usable resolution and increases the cost of large-scale pretraining. Subquadratic alternatives such as linear attention and state-space models reduce this cost, but often serialize images into 1D token streams and weaken the 2D spatial structure important for vision. Generalized Spatial Propagation Networks (GSPN) instead propagate context directly on the 2D grid through line-scan recurrences, achieving near-linear complexity without positional embeddings, but have seen little use as foundation-scale encoders. We present C-GSPN, a foundation-scale vision encoder based on 2D spatial propagation. C-GSPN makes the operator practical through three improvements: (1) a fast GSPN CUDA kernel that fuses per-step launches into a single warp-specialized implementation with shared-memory tiling, coalesced access, and a compact multi-channel propagation, reaching over 90% of peak memory bandwidth and running up to 40--52x faster than the original GSPN implementation; (2) a compressed latent-space propagation block with fused normalization, which turns kernel-level speed into block- and model-level efficiency; and (3) a two-stage cross-operator distillation recipe that trains the new architecture from an attention teacher without the cost of from-scratch foundation-scale training. Distilled with 600M image-text pairs, C-GSPN matches an isomorphic ViT baseline with 15% fewer parameters, improves ADE20K segmentation by +2.1%, transfers to high resolution with a fraction of the data needed from scratch, and delivers a 4x end-to-end block speedup at 2K with single-pass, tiling-free inference.
May 29, 2026

SOCO: Benchmarking Semantic Object Correspondence in Vision Foundation Models

Measuring structured object understanding in vision foundation models remains challenging due to inconsistent evaluation protocols and limited part-level supervision. Semantic correspondence (SC) evaluates this capability by testing whether object parts can be matched across instances and categories under large variations in appearance, viewpoint, and geometry. To enable a systematic SC evaluation, we introduce SOCO, a new benchmark for Semantic Object Correspondence that introduces a taxonomy of correspondence types and provides consistent, functionally meaningful keypoint annotations across 100 categories and over 1M correspondence pairs. In addition, SOCO includes keypoint language descriptions, enabling the evaluation of large vision-language models (LVLMs) and their fine-grained part-level understanding. Comprehensive experiments reveal that (i) vision foundation backbones encode strong semantic structure but transfer correspondences poorly across related categories and only partially capture object-part position, (ii) LVLMs are stronger at text-prompted part localization than at visual-reference cross-image matching, exposing a gap between language-grounded localization and fine-grained visual correspondence, and (iii) correspondence performance predicts performance on dense downstream tasks, including segmentation, tracking, 3D pose estimation, and 3D detection, more strongly than ImageNet classification. Together, these findings position SOCO as a benchmark for structured, part-level representation quality in vision and multimodal foundation models.
May 28, 2026

Towards Consistent Video Geometry Estimation

This work presents ViGeo, a feed-forward foundation model for recovering spatially dense and temporally consistent geometry from video sequences. Built upon a plain transformer architecture without task-specific architectural modifications, ViGeo supports streaming, full-sequence, and long-video inference within a unified model. The key design is dynamic chunking attention, which exposes the model to both bidirectional and causal temporal contexts during training and allows it to adapt its attention pattern at test time without retraining. To improve supervision quality, we further introduce a completion-based data refinement framework. This framework trains a video depth completion teacher that conditions on sparse and noisy annotations and exploits video/multi-view context to produce dense, temporally coherent, and geometrically reliable training targets. Beyond depth and point maps, ViGeo also predicts surface normals within the same framework. Trained solely on public datasets, ViGeo achieves state-of-the-art performance across online, offline, and long-video depth estimation, surface normal estimation, and video point map estimation.
May 26, 2026

JetViT: Efficient High-Resolution Vision Transformer with Post-Training Attention Search

We introduce JetViT, a novel family of hybrid-architecture Vision Transformer (ViT) models that match the accuracy of state-of-the-art full-attention vision foundation models while achieving substantially higher inference efficiency on high-resolution images. At the core of our approach is Post-Training Attention Search, a post-training acceleration framework that converts pre-trained full-attention ViTs into efficient hybrid-attention variants by identifying and replacing redundant full-attention blocks with linear or window-attention blocks. By inheriting the MLP and attention weights from the base model, Post-Training Attention Search efficiently explores the architectural design space through three key steps: (1) optimizing the linear-attention block design; (2) finding the best combination of linear-attention and window-attention blocks; and (3) identifying and preserving critical full-attention blocks. We evaluate JetViT on two representative high-resolution vision foundation models, DINOv3 and DepthAnythingV2. On the NVIDIA H100 GPU, JetViT achieves up to 1.79x higher throughput and up to 44.81% lower latency without sacrificing accuracy. We will release our code and accelerated ViT models soon.
May 26, 2026

Sparse-LiDAR Prompting of Monocular Geometry Foundations: An Empirical Study Toward Long-Range Driving Depth

Sparse-LiDAR-prompted depth foundation models (PromptDA, Prior Depth Anything, DMD3C) have shown strong results on indoor scenes or within KITTI's standard 80-meter evaluation cap. However, two limitations remain: (i) systematic distance-stratified evaluation in long-range driving regimes (50-150 m) is largely absent; (ii) prior approaches built on disparity-based foundations rely on pre-interpolated dense priors, leaving truly sparse LiDAR injection on point-map foundations (e.g., MoGe-2, NeurIPS 2025) unexplored. We present SLIM (Sparse-LiDAR Injected Monocular geometry), the first adaptation of MoGe-2 to accept truly sparse LiDAR input. SLIM integrates a partial-convolution sparse encoder with a multi-scale fusion neck that fuses LiDAR features into the point-map decoder at five scales. We adopt density-agnostic training (random injection ratio in [0.005, 0.30]) so a single model serves diverse input densities. On Virtual KITTI and CARLA, SLIM reduces the absolute relative error of the MoGe-2 baseline by approximately 39-51% at 100-150 m. Ablation across six injection ratios shows partial-convolution injection improves both AbsRel and RMSE on Virtual KITTI in all six settings; on CARLA, AbsRel improves in five of six settings (one near-tie at 0.015 differs by 0.0013), and RMSE is comparable across encoders, with partial-convolution improving in three settings (by up to 0.31 unit) and losing by at most 0.11 unit in the other three.
May 25, 2026

DeCoDrift: Stabilizing Decoder Coupling in Closed-Loop Foundation Segmentation

Foundation segmentation models such as Segment Anything Model (SAM) are now routinely used in iterative pipelines, where each predicted mask is fed back as the next prompt. This practice turns segmentation into a closed-loop dynamical process, yet the decoder-level behavior of these systems remains largely unexamined. We show that this feedback loop can induce a previously overlooked failure mode, decoder coupling drift, in which the mask decoder's cross-attention progressively loses alignment with the target object, causing errors to accumulate across iterations. We study this phenomenon by instrumenting SAM's mask decoder and deriving ground-truth-free measures of prompt-image coupling, attention stability, and temporal consistency. On volumetric electron microscopy data, these decoder-internal signals reveal that standard iterative prompting systematically degrades attention alignment and temporal coherence relative to oracle-anchored feedback. We then formalize iterative prompting as a discrete-time dynamical system and show how proximal anchoring reduces error amplification in the feedback loop. Building on this analysis, we introduce DeCoDrift, a training-free inference-time stabilization framework that constrains prompt updates and preserves decoder coupling across iterations. Across extensive experiments, DeCoDrift consistently improves attention stability, temporal coherence, and segmentation quality over standard iterative prompting, without retraining or ground-truth supervision. More broadly, our results show that decoder-internal dynamics are not merely diagnostic: they provide actionable signals for stabilizing foundation segmentation models in closed-loop use.
May 24, 2026

Cross-Domain Generalization Limits of Vision Foundation Models in Facial Deepfake Detection

The rapid evolution of generative models has enabled the creation of hyper-realistic facial deepfakes, exposing a critical vulnerability in modern digital forensics: the inability of detectors to generalize to unseen manipulation techniques. Traditional networks suffer from representation collapse, overfitting to localized artifact fingerprints of specific training generators. This work investigates whether modern Vision Foundation Models can serve as generalizable, out-of-the-box feature extractors capable of tracking forensic anomalies across entirely unseen generative manifolds. We conduct a systematic cross-domain evaluation comparing three foundational learning paradigms: fully supervised macro-semantic features (RoPE-ViT), pure self-supervised geometric features (DINOv3), and multi-teacher agglomerative representations (NVIDIA C-RADIOv4-H). By deploying frozen backbones subjected to downstream linear probing, we map the performance limitations of these architectures on the challenging DF40 benchmark. Our empirical findings expose the intrinsic trade-offs between pre-training paradigms and parameter scale, proving that while foundation models retain high discriminative capabilities for entire face synthesis, localized face editing techniques expose fundamental boundaries in linear probe evaluation structures. Source code and model weights are available in http://github.com/mribrahim/deepfake
May 23, 2026

The Perception-Physics Paradox: Probing Scientific Alignment with TC-Bench

While Vision Foundation Models (VFMs) excel at predictive tasks on satellite imagery, their performance can arise from visual correlations rather than underlying structural invariants, making even perception-based out-of-distribution accuracy a poor proxy for scientific utility. As a result, models may look correct without reasoning correctly, a discrepancy we term the Perception-Physics Paradox. To address this gap, we introduce scientific alignment as an implicit objective for representation learning in scientific domains. We study a principled, testable aspect of scientific alignment through structural isomorphism, which requires latent representations to uniquely identify physical systems up to a linear reparameterization. This perspective induces a hierarchy of necessary conditions and yields a systematic probing protocol for physical and causal interpretability. To operationalize this framework, we release TC-Bench, a global, reproducible benchmark dataset with an automated construction pipeline for tropical cyclone research, and show that current VFMs rely on visual shortcuts that collapse in intense regimes, indicating that scientific alignment does not arise as a natural byproduct of scaling alone.
May 22, 2026

Planktonzilla: Multimodal dataset and models for understanding plankton ecosystems

Marine plankton underpin aquatic food webs and play a key role in global CO2 sequestration, making reliable species identification critical for understanding ocean health and climate feedbacks. Existing classification models perform well on individual collections but fail to generalize across instruments and environments due to isolated training datasets and inconsistent labels. To address this, we introduce Planktonzilla-17M, a unified dataset consolidating publicly available plankton image collections spanning thirteen imaging systems. It comprises 17.4 million images with standardized taxonomy and geo-environmental metadata, including 3.74 million plankton images spanning over 602 taxonomic classes, of which 201 are identified at the species level, making it the largest and most comprehensive plankton image dataset to date. Using this large-scale dataset, we perform a controlled comparison between supervised and CLIP-style image--text training on a shared ViT backbone. We find that a supervised classifier matches or exceeds CLIP-style training when trained using taxonomic lineage as text. We further observe that BioCLIP and BioCLIP2 perform poorly on plankton in zero-shot and few-shot settings. Leveraging Planktonzilla-17M improves plankton classification performance, highlighting the limitations of current biological foundation models in marine imaging domains.
May 21, 2026

Dithering Defense: Adversarial Robustness of Vision Foundation Models via Multi-Level Floyd-Steinberg Dithering

Vision foundation models are widely used as frozen backbones across many downstream tasks, making them a single point of failure under adversarial attack. We study multi-level Floyd-Steinberg error-diffusion dithering as a lightweight, model-agnostic input transformation that disrupts adversarial perturbations while preserving semantic content. Unlike prior work, which was limited to binary dithering, grayscale CIFAR-10, and a single small model trained from scratch, we evaluate across six tasks (classification, segmentation, depth estimation, retrieval, captioning, visual question answering), two model families (DINOv2, PaliGemma), and three attacks of increasing strength (PGD, MI-FGSM, SIA), as well as an adaptive attacker using a straight-through estimator. Our results show that Floyd-Steinberg dithering at intermediate quantization levels, especially when combined with post-processing blur, exceeds or matches all tested baselines, including diffusion-based denoising, with substantially less degradation on clean inputs.