CVPR 2026 论文列表

The emergence of Large Vision-Language Models (LVLMs) has significantly advanced video understanding capabilities. However, existing benchmarks focus predominantly on coarse-grained tasks such as action segmentation, classification, captioning, and retrieval. Furthermore, these benchmarks often rely on entities that can be easily identified verbally, like household objects, animals, human subjects, etc., limiting their applicability to complex, in-the-wild video scenarios. But, many applications such as furniture assembly, cooking, etc., require step-by-step fine-grained spatio-temporal understanding of the video, which is not sufficiently evaluated in current benchmarks.To address this gap, we introduce Flat-Pack Bench, a novel benchmark centered on furniture assembly tasks. Our benchmark evaluates LVLMs on nuanced tasks, including temporal ordering of assembly actions, temporal localization of assembly state, understanding part mating, and tracking, using multiple-choice questions paired with visual prompts highlighting relevant parts as references for fine-grained questions. Our experiments reveal that state-of-the-art LVLMs struggle significantly with fine-grained spatio-temporal reasoning, highlighting their limitations in effectively leveraging temporal information from videos, limited tracking ability, and understanding of spatial interactions like physical contact.

We present Lumosaic, a compact active hyperspectral video system designed for real-time capture of dynamic scenes. Our approach combines a programmable narrowband LED array with a coded-exposure-pixel (CEP) camera capable of high-speed pixel-wise exposure, thereby enabling joint encoding of scene information across space, time, and wavelength within each video frame. Unlike passive snapshot systems that divide light across multiple spectral channels simultaneously and assume no motion during a frame's exposure, Lumosaic actively synchronizes illumination and sub-frame exposures to improve photon utilization and preserve spectral fidelity under motion. A learning-based reconstruction pipeline then recovers 31-channel hyperspectral (400-700 nm) video at 30 fps and VGA resolution, producing temporally coherent and spectrally accurate reconstructions. Experiments on synthetic benchmarks and real-world dynamic scenes demonstrate that Lumosaic significantly improves reconstruction fidelity and temporal stability over existing snapshot hyperspectral imaging systems, enabling robust hyperspectral video across diverse materials and motion conditions.

Image editing models are advancing rapidly, yet comprehensive evaluation remains a significant challenge. Existing image editing benchmarks generally suffer from limited task scopes, insufficient evaluation dimensions, and heavy reliance on manual annotations, which significantly constrain their scalability and practical applicability. To address this, we propose I2I-Bench, a comprehensive benchmark for image-to-image editing models, which features (i) diverse tasks, encompassing 10 task categories across both single-image and multi-image editing tasks, (ii) comprehensive evaluation dimensions, including 30 decoupled and fine-grained evaluation dimensions with automated hybrid evaluation methods that integrate specialized tools and large multimodal models (LMMs), and (iii) rigorous alignment validation, justifying the consistency between our benchmark evaluations and human preferences.Using I2I-Bench, we benchmark numerous mainstream image editing models, investigating the gaps and trade-offs between editing models across various dimensions. We will open-source all components of I2I-Bench to facilitate future research.

Hardware constraints make it challenging to simultaneously acquire hyperspectral images (HSIs) with both high spatial and high spectral resolutions. A promising solution is to fuse low-resolution HSI (LR-HSI) with high-resolution multispectral images (HR-MSI) to generate high-resolution HSI (HR-HSI). Recently, diffusion models have introduced possibilities for HSI super-resolution, but suffer from low-efficiency sampling, detail-limited generation, and insufficient denoising. To address these issues, we propose an Edge-aware Multimodal Residual Diffusion Model (EMR-Diff). Specifically, multimodal residual mechanism is introduced to facilitate efficient information transfer among HR-MSI, LR-HSI, and HR-HSI, significantly improving the fusion efficiency. Edge-aware noise strategy is designed by exploiting the edge information of HR-MSI, which guides the model to prioritize high-frequency detail reconstruction by applying stronger noise perturbations to edge regions. In addition, we propose a Bilateral Attention Fusion UNet and design a multi-scale supervision mechanism to enable progressive reconstruction and collaborative optimization of spectral and spatial features. Extensive experiments demonstrate that our method achieves superior performance over existing approaches in both quantitative metrics and visual quality.

Federated Prompt Learning (FPL) has recently attracted increasing attention for its ability to leverage large-scale vision-language models such as CLIP within federated learning frameworks. While existing studies have advanced FPL through personalization strategies to enhance client-specific performance, personalized models often suffer severe degradation when deployed across unseen domains due to distribution shifts.In this paper, we take the first step toward exploring Test-Time FPL (TTFPL), aiming to bridge the cross-domain performance gap with minimal effort, requiring only unlabeled target-domain data. We propose COTE, a tri-prompt controllable TTFPL framework that dynamically balances three complementary prompts: the global prompt from standard FPL, the local prompt from personalized FPL, and the frozen CLIP prompt.Specifically, we introduce a novel confidence-guided Model-Data Alignment (MoDA) metric in COTE that quantifies alignment at both macro and micro levels, capturing the consistency between model predictions and data distributions. By integrating MoDA with model confidence, COTE adaptively adjusts the contribution of each prompt at test time, enabling robust generalization across heterogeneous clients and unseen domains without requiring labeled data.Extensive experiments on multiple benchmark datasets demonstrate that our method consistently improves target-domain performance, setting a new direction for adaptive FPL.

Human motion analysis tasks, such as temporal 3D pose estimation, motion prediction, and motion in-betweening, play an essential role in computer vision. However, current paradigms suffer from severe fragmentation. First, the field is split between "perception" models that understand motion from video but only output text, and "generation" models that cannot perceive from raw visual input. Second, generative MLLMs are often limited to single-frame, static poses using dense, parametric SMPL models, failing to handle temporal motion. Third, existing motion vocabularies are built from skeleton data alone, severing the link to the visual domain. To address these challenges, we introduce Superman, a unified framework that bridges visual perception with temporal, skeleton-based motion generation. Our solution is twofold. First, to overcome the modality disconnect, we propose a Vision-Guided Motion Tokenizer. Leveraging the natural geometric alignment between 3D skeletons and visual data, this module pioneers robust joint learning from both modalities, creating a unified, cross-modal motion vocabulary. Second, grounded in this motion language, a single, unified MLLM architecture is trained to handle all tasks. This module flexibly processes diverse, temporal inputs, unifying 3D skeleton pose estimation from video (perception) with skeleton-based motion prediction and in-betweening (generation). Extensive experiments on standard benchmarks, including Human3.6M, demonstrate that our unified method achieves state-of-the-art or competitive performance across all motion tasks. This showcases a more efficient and scalable path for generative motion analysis using skeletons.

In recent years, significant progress has been made in both image generation and generated image detection. Despite their rapid, yet largely independent, development, these two fields have evolved distinct architectural paradigms: the former predominantly relies on generative networks, while the latter favors discriminative frameworks. A recent trend in both domains is the use of adversarial information to enhance performance, revealing potential for synergy. However, the significant architectural divergence between them presents considerable challenges. Departing from previous approaches, we propose **UniGenDet**: a **Uni**fied generative-discriminative framework for co-evolutionary image **Gen**eration and generated image **Det**ection. To bridge the task gap, we design a symbiotic multimodal self-attention mechanism and a unified fine-tuning algorithm. This synergy allows the generation task to improve the interpretability of authenticity identification, while authenticity criteria guide the creation of higher-fidelity images. Furthermore, we introduce a detector-informed generative alignment mechanism to facilitate seamless information exchange. Extensive experiments on multiple datasets demonstrate that our method achieves state-of-the-art performance. Code: https://github.com/Zhangyr2022/UniGenDet.

Although foundation models (e.g. SAM) perform remarkably in medical image segmentation, its high computational complexity limits deployment. Knowledge distillation (KD) allows lightweight models to inherit the representational capabilities of large models, thereby mitigating this issue. Existing KD methods enhance student performance, but due to teacher-student different feature advantages, they neglect to internalize and integrate student's semantic information adaptively after knowledge transfer, causing poor knowledge assimilation and limiting gains and generalization. To address this limitation, we propose a novel medical image segmentation framework, which is infusion to assimilation distillation (IAD). In Knowledge Infusion Stage (KIS), to semantically align teacher-student prediction distributions, soft-label distillation is combined with class-weighted prototype alignment strategy. In Knowledge Assimilation Stage (KAS), to promote adaptively semantic assimilation, a contrastive semantic self-optimization strategy refines student predictions through positive and negative sample pairs and imposes reverse constraints on encoder features to enhance semantic consistency. IAD achieves DICE gains of 4.32% on Synapse, 1.85% on ACDC, and 2.42% on Polyp datasets, and delivers an average 4.16% generalization gain on ISIC2018, PH2, BUSI, and STU datasets, outperforming mainstream KD methods. Code is available at https://github.com/hjklearn/IAD.

Vision-language models (VLMs) have achieved impressive performance across a wide range of multimodal reasoning tasks, but they often struggle to disentangle fine-grained visual attributes and reason about underlying causal relationships. In-context learning (ICL) offers a promising avenue for VLMs to adapt to new tasks, but its effectiveness critically depends on the selection of demonstration examples. Existing retrieval-augmented approaches typically rely on passive similarity-based retrieval, which tends to select correlated but non-causal examples, amplifying spurious associations and limiting model robustness. We introduce CIRCLES (Composed Image Retrieval for Causal Learning Example Selection), a novel framework that actively constructs demonstration sets by retrieving counterfactual-style examples through targeted, attribute-guided composed image retrieval. By incorporating counterfactual-style examples, CIRCLES enables VLMs to implicitly reason about the causal relations between attributes and outcomes, moving beyond superficial correlations and fostering more robust and grounded reasoning. Comprehensive experiments on four diverse datasets demonstrate that CIRCLES consistently outperforms existing methods across multiple architectures, especially on small-scale models, with pronounced gains under information scarcity. Furthermore, CIRCLES retrieves more diverse and causally informative examples, providing qualitative insights into how models leverage in-context demonstrations for improved reasoning. Our code is available at https://github.com/gzxiong/CIRCLES.

In surgical training for medical students, proficiency development relies on expert-led skill assessment, which is costly, time-limited, difficult to scale, and its expertise remains confined to institutions with available specialists. Automated AI-based assessment offers a viable alternative, but progress is constrained by the lack of datasets containing realistic trainee errors and the multi-view variability needed to train robust computer vision approaches. To address this gap, we present Surgical-Hands (SHANDS), a large-scale multi-view video dataset for surgical hand-gesture and error recognition for medical training. SHANDS captures linear incision and suturing using five RGB cameras from complementary viewpoints, performed by 52 participants (20 experts and 32 trainees), each completing three standardized trials per procedure. The videos are annotated at the frame level with 15 gesture primitives and include a validated taxonomy of 8 trainee error types, enabling both gesture recognition and error detection. We further define standardized evaluation protocols for single-view, multi-view, and cross-view generalization, and benchmark state-of-the-art deep learning models on the dataset. SHANDS is publicly released to support the development of robust and scalable AI systems for surgical training grounded in clinically curated domain knowledge.

Occlusion presents two critical challenges for person re-identification (Re-ID): feature interference and information loss. While existing efforts have explored occlusion-aware data augmentation and feature reconstruction to mitigate these issues, the former often fails to address erroneous matches caused by similar occlusion patterns and background distractions, whereas the latter typically introduces significant computational overhead. To overcome these limitations, we propose a Consistent Occlusion and Prompt Enhancement (COPE) network. COPE incorporates a Cross-Identity Consistent Occlusion (CICO) module that applies identical occlusions across different identities and encourages feature similarity in the same occluded regions across different identities to reduce occlusion feature interference. A Prompt Background Filling (PBF) module leverages vision-language alignment to generate foreground heatmaps and performs random background filling, enhancing feature robustness under varying backgrounds. Additionally, a lightweight Prompt Similarity Scoring (PSS) module refines retrieval similarity by utilizing prompt-guided reliability scores. Extensive experiments on both occluded and holistic Re-ID benchmarks demonstrate that COPE consistently outperforms existing methods. Notably, it achieves 82.4% Rank-1 accuracy and 76.4% mAP on the challenging Occluded-Duke dataset. The code is available at https://github.com/Cecoming/COPE.

Current video vision language models (VLMs) process information passively, lacking the ability to dynamically plan their analysis or perform joint reasoning across crucial modalities such as video and audio. To address this, we introduce Hippocampal Sensing (HippoSense), a learning paradigm inspired by hippocampus that shifts the focus from temporal predictive sensing to cross-modal predictive sensing. The core objective of HippoSense is to train the model to anticipate current status's audio-caption summarizations from video and vice versa. We present HippoVLM, a video VLM that operationalizes this paradigm. Instead of passively ingesting all data, HippoVLM actively reasons about its information needs using Chain-of-Thought (CoT). Our training process is twofold: we first finetune HippoVLM with HippoSense, and then apply a novel contrastive Reinforcement Learning (RL) algorithm, Video-Audio Negative-aware Optimization (VANAO), to optimize this selective co-reasoning process. This approach proves highly effective: despite their significantly smaller size, our HippoVLM model achieve competitive performance to massive MLLMs like GPT-4o and Gemini 1.5 Pro on multiple video VQA benchmarks.

Machine Unlearning (MU), erasing undesirable content from Artificial Intelligence (AI) models, plays an essential role in developing safe and trustworthy AI systems.Despite notable advances, the baseline MU methods rely on retraining from scratch without the data to be removed, which is computationally expensive and financially prohibitive.To address this challenge, we propose a simple yet efficient training-free and retain-set-free MU algorithm designed explicitly as a diagnostic baseline: Machine Unlearning pH-Test (MUpHT).It is designed to serve as a practical evaluation reference for future MU methods.Our method eliminates the low dimensional subspaces associated with undesirable concepts from the space spanned by the model's weight vectors, thereby rendering the model "blind" to these undesirable contents. Additionally, we extend our retain-aware variant to handle entangled features by leveraging a generalized Rayleigh quotient over the undesirable and retain sets, enabling an efficient tradeoff between preserving retained knowledge and suppressing undesirable knowledge.Our method enables evaluation of MU across diverse visual tasks, including concept erasure for classification, image generation, and multimodal applications.By producing an unlearned model instantly from only a few samples, our method serves as a quick litmus test for MU.

While Multimodal Large Language Models (MLLMs) excel at vision-language tasks, the cost of their language-driven training on internal visual foundational competence remains unclear. In this paper, we conduct a detailed diagnostic analysis to unveil a pervasive issue: visual representation degradation in MLLMs. Specifically, we find that compared to the initial visual features, the visual representation in the middle layers of LLM exhibits both a degradation in global function and patch structure. We attribute this phenomenon to a visual sacrifice driven by the singular text-generation objective, where the model compromises its visual fidelity to optimize for answer generation. We argue that a robust MLLM requires both strong cross-modal reasoning and core visual competence, and propose Predictive Regularization (PRe) to force degraded intermediate features to predict initial visual features, thereby maintaining the inherent visual attributes of the MLLM's internal representations. Extensive experiments confirm that mitigating this visual degradation effectively boosts vision-language performance, underscoring the critical importance of fostering robust internal visual representations within MLLMs for comprehensive multimodal understanding.

Can warping tokens, rather than pixels, help multimodal large language models (MLLMs) understand how a scene appears from a nearby viewpoint? While MLLMs perform well on visual reasoning, they remain fragile to viewpoint changes, as pixel-wise warping is highly sensitive to small depth errors and often introduces geometric distortions. Drawing on theories of mental imagery that posit part-level structural representations as the basis for human perspective transformation, we examine whether image tokens in ViT-based MLLMs serve as an effective substrate for viewpoint changes. We compare forward and backward warping, finding that backward token warping, which defines a dense grid on the target view and retrieves a corresponding source-view token for each grid point, achieves greater stability and better preserves semantic coherence under viewpoint shifts. Experiments on our proposed ViewBench benchmark demonstrate that token-level warping enables MLLMs to reason reliably from nearby viewpoints, consistently outperforming all baselines including pixel-wise warping approaches, spatially fine-tuned MLLMs, and a generative warping method.

Deep learning-based watermarking has made remarkable progress in recent years. To achieve robustness against various distortions, current methods commonly adopt a training strategy where a \underline s ingle \underline r andom \underline d istortion (SRD) is chosen as the noise layer in each training batch. However, the SRD strategy treats distortions independently within each batch, neglecting the inherent relationships among different types of distortions and causing optimization conflicts across batches. To address this issue, we propose a novel training strategy that enhances robustness and generalization via \underline meta -learning with \underline f eature \underline c onsistency (Meta-FC). Specifically, we randomly sample multiple distortions from the noise pool to construct a meta-training task, while holding out one distortion as a simulated "unknown" distortion for the meta-testing phase.Through meta-learning, the model is encouraged to identify and utilize neurons that exhibit stable activations across different types of distortions, mitigating the optimization conflicts caused by the random sampling of diverse distortions in each batch.To further promote the transformation of stable activations into distortion-invariant representations, we introduce a feature consistency loss that constrains the decoded features of the same image subjected to different distortions to remain consistent.Extensive experiments demonstrate that, compared to the SRD training strategy, Meta-FC improves the robustness and generalization of various watermarking models by an average of 1.59%, 4.71%, and 2.38% under high-intensity, combined, and unknown distortions. Code has been made \href https://github.com/007-li/Meta-FC open-source .

Monocular depth estimation is essential for applications such as robotics. The complementary characteristics of event and image modalities have inspired fusion-based methods for robust depth estimation. However, existing methods rely on convolutional or attention-based architectures, which either have limited capacity for long-range modeling or incur high computational cost, making them less suitable for depth estimation over long sequences. Moreover, effective image-event fusion remains challenging, since most methods directly fuse features without addressing the domain gap and representational differences between raw events and images, resulting in semantic bias and degraded performance. In this work, we propose AIMDepth, an Asymmetric Image-Event Mamba framework for monocular depth estimation, built on state space models for linear complexity and accurate prediction. To alleviate input-domain misalignment, we introduce a Spectral Cross-modal Prior Guidance (SCPG) for bidirectional prior injection at the input level. To reduce the imbalance between sparse events and dense images, we design an asymmetric modal-aware Encoder (AME) with separate encoding paths and feature-level alignment. We further develop a Modality-interactive Local Refinement (ModiLocal) to enable hierarchical interaction and fine-grained alignment. Experiments on public datasets show that AIMDepth achieves state-of-the-art performance in complex environments.

Optical Character Recognition (OCR) is fundamental to Vision-Language Models (VLMs) and high-quality data generation for LLM training. Yet, despite progress in average OCR accuracy, state-of-the-art VLMs still struggle with detecting sample-level errors and lack effective unsupervised quality control.We introduce Consensus Entropy (CE), a training-free, model-agnostic metric that estimates output reliability by measuring inter-model agreement entropy. The core insight is that correct predictions converge in output space, while errors diverge. Based on CE, we develop CE-OCR, a lightweight multi-model framework that verifies outputs by ensemble agreement, selects the best outputs, and further improves efficiency through adaptive routing. Experiments demonstrate that CE is robust for quality verification, improving F1 scores by 42.1% over VLM-as-Judge. CE-OCR achieves consistent OCR gains, outperforming self-consistency and single-model baselines at the same cost. Notably, CE requires no training or supervision, enabling plug-and-play integration.

Large Vision-Language Models (VLMs) are increasingly deployed across diverse applications, such as AI agents, yet remain vulnerable to targeted adversarial attacks. However, the practical robustness of such attacks often remains unclear with limited evaluation under defenses. Diffusion-based purification (DBP), a widely adopted black-box defense, effectively blocks current attacks by removing adversarial perturbations via generative diffusion. Prior DBP evasion attacks target white-box image classifiers and are ill-suited to VLMs, incurring high computational costs and gradient instability when adapted. In this paper, we present PureProof, a black-box targeted attack on VLMs resilient to DBP. It consists of three core components. Stochastic Reverse Alignment (SRA) guides adversarial optimization via single-step reverse prediction, avoiding costly full-trajectory backpropagation. Adaptive Re-noising Augmentation (ARA) mitigates diffusion stochasticity through timestep-adaptive re-noising. Self-Consistency Regularization (SCR) stabilizes optimization by promoting local temporal coherence. Extensive experiments on open-source and commercial VLMs show that PureProof consistently outperforms prior attacks against DBP and achieves strong noise resilience, revealing critical vulnerabilities in VLMs and offering broader safety implications for real-world VLM deployments, including emerging agentic settings.