CVPR 2026 Papers

We aim to learn a joint representation between inertial measurement unit (IMU) signals and 2D pose sequences extracted from video, enabling accurate cross-modal retrieval, temporal synchronization, subject and body-part localization, and action recognition. To this end, we introduce MoBind, a hierarchical contrastive learning framework designed to address three challenges: (1) filtering out irrelevant visual background, (2) modeling structured multi-sensor IMU configurations, and (3) achieving fine-grained, sub-second temporal alignment. To isolate motion-relevant cues, MoBind aligns IMU signals with skeletal motion sequences rather than raw pixels. We further decompose full-body motion into local body-part trajectories, pairing each with its corresponding IMU to enable semantically grounded multi-sensor alignment. To capture detailed temporal correspondence, MoBind employs a hierarchical contrastive strategy that first aligns token-level temporal segments, then fuses local (body-part) alignment with global (body-wide) motion aggregation. Evaluated on mRi, TotalCapture, and EgoHumans, MoBind consistently outperforms strong baselines across all four tasks, demonstrating robust fine-grained temporal alignment while preserving coarse semantic consistency across modalities.

Federated learning (FL) allows distributed clients to collaboratively train a global model in a privacy-preserving manner. However, one major challenge is domain skew, where clients' data originating from diverse domains may hinder the aggregated global model from learning a consistent representation space, resulting in poor generalizable ability in multiple domains. In this paper, we argue that the domain skew is reflected in the domain-specific biased features of each client, causing the local model's representations to collapse into a narrow low-dimensional subspace. We then propose Federated Feature Decoupling and Calibration (**F^2DC**), which liberates valuable class-relevant information by calibrating the domain-specific biased features, enabling more consistent representations across domains. A novel component, Domain Feature Decoupler (DFD), is first introduced in F^2DC to determine the robustness of each feature unit, thereby separating the local features into domain-robust features and domain-related features. A Domain Feature Corrector (DFC) is further proposed to calibrate these domain-related features by explicitly linking discriminative signals, capturing additional class-relevant clues that complement the domain-robust features. Finally, a domain-aware aggregation of the local models is performed to promote consensus among clients. Empirical results on three popular multi-domain datasets demonstrate the effectiveness of the proposed F^2DC and the contributions of its two modules.

The limited understanding capacity of the visual encoder in Contrastive Language-Image Pre-training (CLIP) has become a key bottleneck for downstream performance. This capacity includes both Discriminative Ability (D-Ability), which reflects class separability, and Detail Perceptual Ability (P-Ability), which focuses on fine-grained visual cues. Recent solutions use diffusion models to enhance representations by conditioning image reconstruction on CLIP visual tokens. We argue that such paradigms may compromise D-Ability and therefore fail to effectively address CLIP's representation limitations. To address this, we integrate contrastive signals into diffusion-based reconstruction to pursue more comprehensive visual representations. We begin with a straightforward design that augments the diffusion process with contrastive learning on input images. However, empirical results show that the naive combination suffers from gradient conflict and yields suboptimal performance. To balance the optimization, we introduce the Diffusion Contrastive Reconstruction (DCR), which unifies the learning objective. The key idea is to inject contrastive signals derived from each reconstructed image, rather than from the original input, into the diffusion process. Our theoretical analysis shows that the DCR loss can jointly optimize D-Ability and P-Ability. Extensive experiments across various benchmarks and multi-modal large language models validate the effectiveness of our method. The code is available at https://github.com/boyuh/DCR.

Vision-Language Models (VLMs) have achieved remarkable progress across tasks such as visual question answering and image captioning. Yet, the extent to which these models perform visual reasoning as opposed to relying on linguistic priors remains unclear. To address this, we introduce VisRes Bench, a benchmark designed to study visual reasoning in naturalistic settings without contextual language supervision. Analyzing model behavior across three levels of complexity, we uncover clear limitations in perceptual and relational visual reasoning capacities. VisRes isolates distinct reasoning abilities across its levels. Level 1 probes perceptual completion and global image matching under perturbations such as blur, texture changes, occlusion, and rotation; Level 2 tests rule-based inference over a single attribute (e.g., color, count, orientation); and Level 3 targets compositional reasoning that requires integrating multiple visual attributes. Across more than 19,000 controlled task images, we find that state-of-the-art VLMs perform near random under subtle perceptual perturbations, revealing limited abstraction beyond pattern recognition. We conclude by discussing how VisRes provides a unified framework for advancing abstract visual reasoning in multimodal research (https://visres-bench.github.io).

Recent progress in 4D representations, such as Dynamic NeRF and 4D Gaussian Splatting (4DGS), has enabled dynamic 4D scene reconstruction. However, text-driven 4D scene editing remains under-explored due to the challenge of ensuring both multi-view and temporal consistency across space and time during editing.Existing studies rely on 2D diffusion models that edit frames independently, often causing motion distortion, geometric drift, and incomplete editing. We introduce Dynamic-eDiTor, a training-free text-driven 4D editing framework leveraging Multimodal Diffusion Transformer (MM-DiT) and 4DGS. This mechanism consists of Spatio-Temporal Sub-Grid Attention (STGA) for locally consistent cross-view and temporal fusion, and Context Token Propagation (CTP) for global propagation via token inheritance and optical-flow-guided token replacement. Together, these components allow Dynamic-eDiTor to perform seamless, globally consistent multi-view video without additional training and directly optimize pre-trained source 4DGS.Extensive experiments on multi-view video dataset DyNeRF demonstrate that our method achieves superior editing fidelity and both multi-view and temporal consistency prior approaches. Project page for results and code: https://di-lee.github.io/dynamic-eDiTor

Modern neural architectures for 3D point cloud processing contain both convolutional layers and attention blocks, but the best way to assemble them remains unclear. We analyse the role of different computational blocks in 3D point cloud networks and find an intuitive behaviour: convolution is adequate to extract low-level geometry at high-resolution in early layers, where attention is expensive without bringing any benefits; attention captures high-level semantics and context in low-resolution, deep layers more efficiently. Guided by this design principle, we propose a new, improved 3D point cloud backbone that employs convolutions in early stages and switches to attention for deeper layers. To avoid the loss of spatial layout information when discarding redundant convolution layers, we introduce a novel, parameter-free 3D positional encoding, PointROPE. The resulting LitePT model has 3.6x fewer parameters, runs 2x faster, and uses 2x less memory than the state-of-the-art Point Transformer V3, but nonetheless matches or outperforms it on a range of tasks and datasets.

This paper presents VGGT-360, a novel training-free framework for zero-shot, geometry-consistent panoramic depth estimation. Unlike prior view-independent training-free approaches, VGGT-360 reformulates the task as panoramic reprojection over multi-view reconstructed 3D models by leveraging the intrinsic 3D consistency of VGGT-like foundation models, thereby unifying fragmented per-view reasoning into a coherent panoramic understanding. To achieve robust and accurate estimation, VGGT-360 integrates three plug-and-play modules that form a unified panorama-to-3D-to-depth framework: (i) Uncertainty-guided adaptive projection slices panoramas into perspective views to bridge the domain gap between panoramic inputs and VGGT's perspective prior. It estimates gradient-based uncertainty to allocate denser views to geometry-poor regions, yielding geometry-informative inputs for VGGT. (ii) Structure-saliency enhanced attention strengthens VGGT's robustness during 3D reconstruction by injecting structure-aware confidence into its attention layers, guiding focus toward geometrically reliable regions and enhancing cross-view coherence. (iii) Correlation-weighted 3D model correction refines the reconstructed 3D model by reweighting overlapping points using attention-inferred correlation scores, providing a consistent geometric basis for accurate panoramic reprojection. Extensive experiments show that VGGT-360 outperforms both trained and training-free state-of-the-art methods across multiple resolutions and diverse indoor and outdoor datasets. The code is available at https://github.com/Yuanjiayii/VGGT-360.

Multi-modal Large Language Models (MLLMs) show promise in video understanding. However, their reasoning often suffers from thinking drift and weak temporal comprehension, even when enhanced by Reinforcement Learning (RL) techniques like Group Relative Policy Optimization (GRPO). Moreover, existing RL methods usually depend on Supervised Fine-Tuning (SFT), which requires costly Chain-of-Thought (CoT) annotation and multi-stage training, and enforces fixed reasoning paths, limiting MLLMs' ability to generalize and potentially inducing bias. To overcome these limitations, we introduce Summary-Driven Reinforcement Learning (SDRL), a novel single-stage RL framework that obviates the need for SFT by utilizing a Structured CoT format: Summarize - Think - Answer. SDRL introduces two self-supervised mechanisms integrated into the GRPO objective: 1) Consistency of Vision Knowledge (CVK) enforces factual grounding by reducing KL divergence among generated summaries; and 2) Dynamic Variety of Reasoning (DVR) promotes exploration by dynamically modulating thinking diversity based on group accuracy. This novel integration effectively balances alignment and exploration, supervising both the final answer and the reasoning process. Our method achieves state-of-the-art performance on seven public VideoQA datasets.

Vision-Language Models (VLMs) have emerged as a promising paradigm in autonomous driving (AD), providing a unified framework for perception and decisionmaking. However, their real-world deployment is hindered by significant computational overhead when processing high-resolution, multi-view images. This complexity stems from the massive number of visual tokens, which increases inference latency and memory consumption due to the quadratic complexity of self-attention. To address these challenges, we propose Prune2Drive, a plug-and-play visual token pruning framework for multi-view VLMs in AD. Prune2Drive introduces two core innovations: (i) a diversity-aware token selection mechanism that prioritizes semantic and spatial coverage across views, and (ii) a view-adaptive pruning controller that automatically learns optimal pruning ratios based on camera importance to downstream tasks. Unlike prior methods, Prune2Drive requires no model retraining or access to attention maps, ensuring compatibility with modern efficient attention implementations. Extensive experiments on the DriveLM and DriveLMM-o1 benchmarks demonstrate that Prune2Drive achieves significant speedups and memory savings with minimal performance impact. When retaining only 10% of visual tokens, our method achieves a 6.40x speedup in the prefilling phase and consumes only 13.4% of the original FLOPs, with a mere 3% average performance drop on the DriveLM benchmark. Code is available at: https://github.com/MinhaoXiong/Prune2Drive.git

Knowledge distillation (KD) is a standard route to compress Large Language Models (LLMs) into compact students, yet most pipelines uniformly apply token-wise loss regardless of teacher confidence. This indiscriminate supervision amplifies noisy, high-entropy signals and is especially harmful under large teacher-student capacity gaps. We introduce SelecTKD, a plug-and-play Selective Token-Weighted distillation framework that shifts the focus from "how to measure divergence" to "where to apply learning". At each step, the student proposes tokens that are verified by the teacher through a robust propose-and-verify procedure with two variants: greedy Top-k and non-greedy Spec-k. Accepted tokens receive full loss, while rejected tokens are masked or down-weighted. This objective-agnostic design works with on- and off-policy data, induces an implicit curriculum quantified by Token Acceptance Rate (TAR), and stabilizes optimization. Across instruction following, mathematical reasoning, code generation, and a VLM setting, SelecTKD consistently improves strong baselines and achieves state-of-the-art results for small models without architectural changes or extra reference models.

Diffusion models degrade images through noise, and reversing this process reveals an information hierarchy across timesteps. Scale-space theory exhibits a similar hierarchy via low-pass filtering. We formalize this connection and show that highly noisy diffusion states contain no more information than small, downsampled images - raising the question of why they must be processed at full resolution. To address this, we fuse scale spaces into the diffusion process by formulating a family of diffusion models with generalized linear degradations and practical implementations. Using downsampling as the degradation yields our proposed \ours. To support \ours, we introduce \ourmodel , a UNet variant that performs resolution-preserving and resolution-increasing denoising using only the necessary parts of the network. We evaluate our framework on CelebA and ImageNet and analyze its scaling behavior across resolutions and network depths. Our website is available at prateksha.github.io/projects/scale-space-diffusion.

Estimating slide- and patch-level gene expression profiles from pathology images enables rapid and low-cost molecular analysis with broad clinical impact. Despite strong results, existing approaches treat gene expression as a mere slide- or spot-level signal and do not incorporate the fact that the measured expression arises from the aggregation of underlying cell-level expression. To explicitly introduce this missing cell-resolved guidance, we propose a Cell-type Prototype-informed Neural Network (CPNN) that leverages publicly available single-cell RNA-sequencing datasets. Since single-cell measurements are noisy and not paired with histology images, we first estimate cell-type prototypes--mean expression profiles that capture stable gene-gene co-variation patterns. CPNN then learns cell-type compositional weights directly from images and models the relationship between prototypes and observed bulk or spatial expression, providing a biologically grounded and structurally regularized prediction framework. We evaluate CPNN on three slide-level datasets and three patch-level spatial transcriptomics datasets. Across all settings, CPNN achieves the highest performance in terms of Spearman correlation. Moreover, by visualizing the inferred compositional weights, our framework provides interpretable insights into which cell types drive the predicted expression.Code is publicly available at https://github.com/naivete5656/CPNN.

Federated learning (FL) enables collaborative training across clients while preserving privacy. While most existing FL methods assume homogeneous model architectures, client heterogeneity in both data and resources makes this assumption impractical, thus motivating model-heterogeneous FL. To address this problem, we propose Federated Representation Entanglement (FedRE), a framework built upon a novel form of client knowledge termed entangled representation. Specifically, each client aggregates its local representations into a single entangled representation using normalized random weights, and then applies the same weights to integrate the corresponding one-hot label encodings into an entangled-label encoding. Both are subsequently uploaded to the server to train a global classifier. During training, each entangled representation is supervised across categories via its entangled-label encoding, while random weights are re-sampled at each round to introduce diversity, alleviating overconfidence in the global classifier and yielding smoother decision boundaries. Moreover, each client uploads a single entangled representation along with its entangled-label encoding, mitigating the risk of representation inversion attacks and reducing communication overhead. Extensive experiments demonstrate that FedRE achieves an effective trade-off among model performance, privacy protection, and communication overhead. The codes are available at https://github.com/AIResearch-Group/FedRE.

Online micro gesture recognition from hand skeletons is critical for VR/AR interaction but faces challenges due to limited public datasets and task-specific algorithms. Micro gestures involve subtle motion patterns, which make constructing datasets with precise skeletons and frame-level annotations difficult. To this end, we develop a multi-view self-supervised pipeline to automatically generate skeleton data, complemented by heuristic rules and expert refinement for semi-automatic annotation. Based on this pipeline, we introduce OMG-Bench, the first large-scale public benchmark for skeleton-based online micro gesture recognition. It features 40 fine-grained gesture classes with 13,948 instances across 1,272 sequences, characterized by subtle motions, rapid dynamics, and continuous execution. To tackle these challenges, we propose Hierarchical Memory-Augmented Transformer (HMATr), an end-to-end framework that unifies gesture detection and classification by leveraging hierarchical memory banks which store frame-level details and window-level semantics to preserve historical context. In addition, it employs learnable position-aware queries initialized from the memory to implicitly encode gesture positions and semantics. Experiments show that HMATr outperforms state-of-the-art methods by 7.6% in detection rate, establishing a strong baseline for online micro gesture recognition.

Woven fabric materials are widely used in rendering applications, yet designing realistic examples typically involves multiple stages, requiring expertise in weaving principles and texture authoring. Recent advances have explored diffusion models to streamline this process; however, pre-trained diffusion models often struggle to generate intricate yarn-level details that conform to weaving rules. To address this, we present FabricGen, an end-to-end framework for generating high-quality woven fabric materials from textual descriptions. A key insight of our method is the decomposition of macro-scale textures and micro-scale weaving patterns. To generate macro-scale textures free from microstructures, we fine-tune pre-trained diffusion models on a collected dataset of microstructure-free fabrics. As for micro-scale weaving patterns, we develop an enhanced procedural geometric model capable of synthesizing natural yarn-level geometry with yarn sliding and flyaway fibers. The procedural model is driven by a specialized large language model, WeavingLLM, which is fine-tuned on an annotated dataset of formatted weaving drafts, and prompt-tuned with domain-specific fabric expertise. Through fine-tuning and prompt tuning, WeavingLLM learns to design weaving drafts and fabric parameters from textual prompts, enabling the procedural model to produce diverse weaving patterns that stick to weaving principles. The generated macro-scale texture, along with the micro-scale geometry, can be used for fabric rendering. Consequently, our framework produces materials with significantly richer detail and realism compared to prior generative models.

Text-based human motion editing aims to modify existing motion sequences according to natural language instructions while maintaining the consistency of the original motion. Existing diffusion-based approaches often rely on heuristic similarity cues or coarse global conditioning, leading to motion distortion and suboptimal semantic alignment. The key challenge lies in balancing change (i.e. precisely editing target regions) and invariance (i.e. preserving unedited parts). To handle such challenge, we propose an Omni-Supervised Positive-Negative Learning framework, named OmniME. Our method integrates three complementary components: (1) retrospective feature supervision that enforces coarse-to-fine consistency across transformer layers, (2) motion preservation mechanism that focuses on subtle variations accoding to the source-target similarity, and (3) triplet-based semantic alignment that strengthens text-motion correspondence. Together, these components form a unified supervision paradigm that balances change and invariance. Extensive experiments on the MotionFix and STANCE Adjustment datasets demonstrate that OmniME achieves state-of-the-art performance in editing alignment, validating the effectiveness of our unified learning framework. Our source codes and models have been released at: https://github.com/ rocket-ycyer/OmniME.git

Direct Time-of-Flight (dToF) sensors provide highly accurate metric depth and are more robust than indirect ToF systems in challenging real-world conditions. However, their high manufacturing cost and limited photodiode array size produce depth maps that are extremely sparse, low-resolution, and noisy, making them unsuitable for VR/XR, robotics, and 3D perception tasks that require dense metric depth. Existing monocular and depth completion methods struggle to handle the unique sampling patterns and hardware artifacts of dToF devices, and their performance often deteriorates significantly under severe sparsity or noise. We present a generalizable framework for dense metric depth completion from sparse dToF measurements, capable of operating across diverse sensor types, sparsity levels, and noise conditions. Our model employs a depth-guided dual-branch Vision Transformer encoder that processes RGB images and sparse dToF measurements separately, while a masked joint attention module allows depth tokens to reliably guide image features without being overwritten by them. A lightweight decoder reconstructs dense metric depth efficiently, without diffusion-based or refinement-heavy post-processing. To address the scarcity of paired training data, we introduce a comprehensive dToF simulation pipeline that reproduces the characteristics of flash, sub-VGA flash, and rotating sensors, including hardware-induced degradation, irregular sparsity, and realistic noise distributions. Trained entirely on synthetic data, our model achieves strong zero-shot generalization across 6 datasets and 3 real dToF devices, outperforming state-of-the-art approaches in both accuracy and computational efficiency. This establishes a robust and practical solution for dense metric depth completion from sparse direct ToF sensors.

Data matters. In computer vision, data (or pixels) are the primary source of information containing signals that span from low-level attributes to high-level concepts. At scale, the success of modern vision systems has been closely tied to how data is curated for semantic understanding (e.g., ImageNet). Recent trends in spatial intelligence and physical world understanding further highlight the importance of real-world signals that preserve spatial structure, beyond purely semantic signals. This motivates a shift toward curating data that better captures spatially grounded information across diverse environments. In this work, we demonstrate that training on 2B web-crawled images with a self-curation strategy on masked autoencoder (MAE) can learn strong representations for dense prediction tasks, while remaining simple, stable, and efficient. Our model, codenamed "Pixio", is an enhanced masked autoencoder (MAE) with more challenging pre-training tasks and more capable architectures. Pixio yields dense representations achieving promising results across a wide range of dense prediction tasks in the wild, including monocular depth estimation (e.g., Depth Anything), feed-forward 3D reconstruction (i.e., MapAnything), and visual segmentation (e.g., SAM). Our results suggest that data curation can significantly contribute to dense representation learning.

Infrared image super-resolution (IISR) under real-world conditions is a practically significant yet rarely addressed task. Pioneering works are often trained and evaluated on simulated datasets or neglect the intrinsic differences between infrared and visible imaging. In practice, however, real infrared images are affected by coupled optical and sensing degradations that jointly deteriorate both structural sharpness and thermal fidelity. To address these challenges, we propose Real-IISR, a unified autoregressive framework for real-world IISR that progressively reconstructs fine-grained thermal structures and clear backgrounds in a scale-by-scale manner via thermal-structural guided visual autoregression. Specifically, a Thermal-Structural Guidance module encodes thermal priors to mitigate the mismatch between thermal radiation and structural edges. Since non-uniform degradations typically induce quantization bias, Real-IISR adopts a Condition-Adaptive Codebook that dynamically modulates discrete representations based on degradation-aware thermal priors. Also, a Thermal Order Consistency Loss enforces a monotonic relation between temperature and pixel intensity, ensuring relative brightness order rather than absolute values to maintain physical consistency under spatial misalignment and thermal drift. We build FLIR-IISR, a real-world IISR dataset with paired LR-HR infrared images acquired via automated focus variation and motion-induced blur. Extensive experiments demonstrate the promising performance of Real-IISR, providing a unified foundation for real-world IISR and benchmarking. The dataset and code are available at: https://github.com/JZD151/Real-IISR.