CVPR 2026 Papers

We consider the problem of imaging a dynamic scene when scene appearance variations can outpace photon arrivals. Under such conditions, a pixel is effectively "blind" to changes in appearance that occur within the timespan separating the photons it detects, and so the inter-photon interval presents a significant speed barrier to video acquisition systems. To analyze and advance imaging capabilities at the inter-photon limit, we introduce a novel reparameterization of time-varying flux that reveals the intrinsic difficulty of signal reconstruction by relating the Fourier decomposition of a flux function to the number of photons arriving within each oscillation period. We find that inter-photon-limited videography of general scenes is underexplored and beyond the reach of existing reconstruction techniques. To this end, we introduce Neural Flux Fields---a technique that combines statistical modeling of photon arrival with intrinsic priors of a neural network to achieve robust videography at the inter-photon limit. Using this approach, we demonstrate never-before-seen capabilities in video reconstruction across a range of captured single-photon video datasets spanning the inter-photon-limited regime.

Video data is more cost-effective than motion capture data for learning 3D character controllers, yet using it to generate realistic and physically plausible motions remains challenging. Previous approaches typically rely on off-the-shelf motion reconstruction techniques to extract 3D kinematic trajectories for physics-based imitation. However, these approaches are fundamentally limited by the physical implausibility of the estimated motions and lack a unified framework for handling non-human subjects and complex human-object interactions (HOI). We tackle this challenge by introducing Mimic2DM, a novel motion imitation framework that learns the control policy directly and solely from 2D motions extracted from videos. By formulating a 2D motion tracking objective, we train a general single-view tracking policy capable of imitating arbitrary reference motions in a physics simulation using exclusively 2D data. Furthermore, by training on 2D motions from diverse viewpoints, our view-agnostic policy implicitly learns 3D motion structures, allowing it to perform full 3D motion tracking simply by aggregating multiple views. To extend this capability, we integrate the tracking policy with an autoregressive transformer-based 2D motion generator, constructing a hierarchical control framework capable of long-horizon motion synthesis and interactive control. We show that the proposed approach is versatile and effectively synthesizes physically plausible and diverse motions across a range of domains, including dancing, soccer dribbling, and animal locomotion, without any reliance on explicit 3D motion data.

Most existing 3D keypoint estimation methods rely on manual annotations or calibrated multi-view images, both of which are expensive to collect.This paper introduces KeyDiff3D, a framework that can accurately predict 3D keypoints from a single image, thus eliminating the need for such expensive data acquisitions.To achieve this, we leverage powerful geometric priors embedded in a pretrained multi-view diffusion model.In our framework, the diffusion model generates multi-view images from a single image, serving as supervision signals to provide 3D geometric cues to our model.We also introduce a 3D feature extractor that transforms implicit 3D priors embedded in the diffusion features into explicit 3D feature volumes.Beyond accurate keypoint estimation, we further introduce a pipeline that enables manipulation of 3D objects generated by the diffusion model.Experimental results on diverse datasets, including Human3.6M, CUB-200-2011, Stanford Dogs, and several in-the-wild and out-of-domain inputs, highlight the effectiveness of our method in terms of accuracy, generalization, and its ability to enable manipulation of 3D objects generated by the diffusion model from a single image.

Estimating the 3D motion of scene points from 2D observations, typically parameterized by optical flow and motion in depth, is a fundamental problem in computer vision. Existing learning-based methods usually rely on supervised regression from densely labeled data, but their dependence on annotations and limited use of geometric constraints restricts generalization, motivating unsupervised solutions. Unsupervised 3D motion estimation is challenging because motion along the viewing direction is unobservable, and optical flow and motion in depth are geometrically coupled, making their separation ambiguous. Event cameras capture per-pixel brightness changes asynchronously with microsecond latency, providing high temporal resolution and motion continuity. Projecting event streams along different axes reveals spatiotemporal expansion and contraction patterns that encode depth variation and geometric structure, offering rich cues for unsupervised estimation. Leveraging these properties, we propose an unsupervised event-based 3D motion estimation framework that jointly models optical flow and motion in depth. We first derive an analytical relationship to infer initial motion in depth from estimated flow and further refine it using a directional expansion modulation module that captures horizontal and vertical expansion-contraction patterns in event projections. Finally, motion in depth is incorporated into optical flow warping under a contrast maximization objective. Experiments on the CarlaEvent3D dataset show that our method achieves competitive accuracy and strong generalization, advancing unsupervised 3D motion estimation in the event domain.

Spatial registration across different visual modalities is a critical but formidable step in multi-modality image fusion for real-world perception. Although several methods are proposed to address this issue, the existing registration-based fusion methods typically require extensive pre-registration operations, limiting their efficiency. To overcome these limitations, a general cross-modality registration method guided by visual priors is proposed for infrared and visible image fusion task, termed FusionRegister. Firstly, FusionRegister achieves robustness by learning cross-modality misregistration representations rather than forcing alignment of all differences, ensuring stable outputs even under challenging input conditions. Moreover, FusionRegister demonstrates strong generality by operating directly on fused results, where misregistration is explicitly represented and effectively handled, enabling seamless integration with diverse fusion methods while preserving their intrinsic properties. In addition, its efficiency is further enhanced by serving the backbone fusion method as a natural visual prior provider, which guides the registration process to focus only on mismatch regions, thereby avoiding redundant operations. Extensive experiments on three datasets demonstrate that FusionRegister not only inherits the fusion quality of state-of-the-art methods, but also delivers superior detail alignment and robustness, making it highly suitable for infrared and visible image fusion method. The code will be available at https://github.com/bociic/FusionRegister.

We introduce an unsupervised approach for segmenting multiscale subcellular objects in 3D volumetric cryo-electron tomography (cryo-ET) images. To this end, we address key challenges such as lack of annotated data, large data volumes, high heterogeneity of subcellular shapes and sizes, and high inter-domain variability of cellular cryo-ET images across different experiments and contexts. Our method requires users to only select a small number of slabs from a few representative tomograms in the dataset. The core of our method is extracting features for the corresponding slabs, leveraging a Stable Diffusion foundation model pretrained on mostly natural images. The feature extraction is followed by a novel heuristic-based feature aggregation strategy, and adaptive thresholding to segment the aggregated features. The resulting masks are refined with pretrained CellPose to split composite regions, and then utilized as pseudo-ground truth for training supervised deep learning models. We validated our unsupervised foundation-model based pipeline on publicly available cryo-ET benchmark datasets, demonstrating performance that closely approximates expert human annotations. This fully automated, data-driven framework enables the mining of multi-scale subcellular patterns, paving the way for accelerated biological discoveries from large-scale cellular cryo-ET datasets.

Dense 3D shape correspondence remains a central challenge in computer vision and graphics as many deep learning approaches still rely on intermediate geometric features or handcrafted descriptors, limiting their effectiveness under non-isometric deformations, partial data, and non-manifold inputs. To overcome these issues, we introduce RINO, an unsupervised, rotation-invariant dense correspondence framework that effectively unifies rigid and non-rigid shape matching. The core of our method is the novel RINONet, a feature extractor that integrates vector-based SO(3)-invariant learning with orientation-aware complex functional maps to extract robust features directly from raw geometry. This allows for a fully end-to-end, data-driven approach that bypasses the need for shape pre-alignment or handcrafted features. Extensive experiments show unprecedented performance of RINO across challenging non-rigid matching tasks, including arbitrary poses, non-isometry, partiality, non-manifoldness, and noise.

Continual unlearning poses the challenge of enabling large vision-language models to selectively refuse specific image-instruction pairs in response to sequential deletion requests, while preserving general utility. However, sequential unlearning updates distort shared representations, creating spurious associations between vision-language pairs and refusal behaviors that hinder precise identification of refusal targets, resulting in inappropriate refusals. To address this challenge, we propose a novel continual unlearning framework that grounds refusal behavior in fine-grained descriptions of visual and textual concepts decomposed from deletion targets. We first identify which visual-linguistic concept combinations characterize each forget category through a concept modulator, then determine how to generate appropriate refusal responses via a mixture of refusal experts, termed refusers, each specialized for concept-aligned refusal generation. To generate concept-specific refusal responses across sequential tasks, we introduce a multimodal, concept-driven routing scheme that reuses refusers for tasks sharing similar concepts and adapts underutilized ones for novel concepts. Extensive experiments on vision-language benchmarks demonstrate that the proposed framework outperforms existing methods by generating concept-grounded refusal responses and preserving the general utility across unlearning sequences.

Recent advances in 3D vision-language models (VLMs) highlight a strong potential for 3D scene understanding and reasoning.However, effectively tokenizing 3D scenes into holistic scene tokens, and leveraging these tokens across diverse 3D understanding tasks, remain highly challenging. We present NDTokenizer3D, a generalist 3D VLM that performs a wide range of 3D scene understanding tasks while naturally supporting human interactions, thereby bridging language-level reasoning with 3D spatial understanding. The core of our approach is a novel three-stage scene tokenization pipeline built upon a Multi-Scale Normal Distributions Transform (NDT) representation, paired with a Multi-Scale NDT Decoder (MSDec).Specifically, NDTokenizer3D first constructs a multi-scale NDT representation from raw high-resolution point clouds, preserving both global context and fine-grained geometric details. Next, the MSDec progressively fuses cross-scale NDT features, producing holistic scene tokens consumable by LLM endpoints. Beyond tokenization, MSDec is repurposed as a general interface for human-interactive prompting (points, boxes, masks) and segmentation-mask decoding, unifying diverse 3D scene understanding tasks within a single architecture. With this compact and unified design, NDTokenizer3D offers a fine-grained, general-purpose 3D VLM, achieving remarkable improvements in 3D Referring Segmentation, 3D Visual Question Answering, and 3D Dense Captioning.

Unsupervised Anomaly Detection (UAD) and anomaly classification are frequently used in industrial and medical scenarios. Specifically, UAD identifies anomalous regions at the fine-grained pixel-level, while anomaly classification distinguishes anomaly types at the anomaly region level. However, existing approaches typically treat these tasks independently and sequentially, overlooking the benefits of jointly training them to suppress Local Visual Ambiguity (LVA) caused by the similarities of different types of anomalies in local visual patterns. Moreover, a multi-task learning framework cannot be directly applied to jointly train the two tasks, since UAD and anomaly classification exhibit feature preference incompatibility. To address these limitations, we propose the Prototype-Guided Semi-Supervised Feature Disentanglement (PG-SFD) framework, which makes a paradigm shift from implicit feature sharing to explicit feature disentanglement and explicitly constructs normal and category prototypes to eliminate implicit normal-abnormal semantic coupling via a Dual-Prototype Disentanglement Module (DPRM). Moreover, for cross-task feature differential injection and gradient conflict mitigation, the Differential Gated Interaction (DGI) and Geometry-Regularized Optimization (GRO) are proposed to form a cohesive framework with DPRM. PG-SFD demonstrates high effectiveness in both UAD tasks and weakly supervised classification tasks. Meanwhile, it exhibits stable performance across multiple types of datasets, including industrial and medical datasets, indicating its strong generalizability.

Unsupervised non-rigid point cloud correspondence aims to predict point-to-point correspondences without annotations. Existing methods leverage the spatial-relation-based feature propagation strategy that includes non-physical connections, which are sensitive to non-rigid deformation. To address this issue, we advocate to learn shape topology robust to non-rigid deformation, and propose the topology-aware feature propagation module integrated into a coarse-to-fine propagation and optimization pipeline. To extract point features robust to non-rigid deformation, we estimate keypoints as superpoints and encode superpoint features with topology weights, which learns reasonable topologies under non-rigid deformation. The vector quantization codebook is leveraged to enhance the original superpoint features with stored representative features across the dataset, improving feature robustness against shape variance. Robust point-wise correspondence is yielded after coarse-to-fine feature fusion and efficient test-time optimization. Extensive experiments on multiple benchmarks demonstrate the state-of-the-art performance of our method.

The task of capturing and rendering 3D dynamic scenes from 2D images has become increasingly popular in recent years. However, most conventional cameras are bandwidth-limited to 30-60 FPS, restricting these methods to static or slowly evolving scenes. While overcoming bandwidth limitations is difficult in general scenes, recent years have seen a flurry of computational imaging methods that yield high-speed videos using conventional cameras for specific scenarios (e.g., motion capture and particle image velocimetry). However, most of these methods require modifications to camera optics or the addition of mechanically moving components, limiting them to a single-view high-speed capture. Consequently, these cannot be readily used to capture a 3D representation of rapid scene motion. In this paper, we propose a novel method to capture and reconstruct a volumetric representation of a high-speed scene using only unaugmented low-speed cameras. Instead of modifying the hardware or optics of each individual camera, we encode high-speed scene dynamics by illuminating the scene with a rapid, sequential color sequence. This results in simultaneous multi-view capture of the scene, in which high-speed temporal information is encoded in the images' color. To construct a high-speed volumetric representation of the dynamic scene, we develop a novel dynamic Gaussian Splatting-based approach that decodes the temporal information from the images. We evaluate our approach on simulated scenes and real-world experiments using a multi-camera imaging setup, showing first-of-a-kind high-speed volumetric scene reconstructions.

Current audio pre-training seeks to learn unified representations for broad audio understanding tasks, but it remains fragmented and is fundamentally bottlenecked by its reliance on weak, noisy, and scale-limited labels. Drawing lessons from vision's foundational pre-training blueprint, we argue that the audio field must first establish its own large-scale, strong supervision framework. We introduce a new data-centric pipeline that leverages a high-fidelity captioner to create SOTA-quality captions and the first Unified Tag System (UTS) that bridges speech, music, and environmental sounds. We then conduct a systematic comparative study of different pre-training objectives on these strong source data. Our experiments suggest that data quality and coverage are the primary drivers of performance, while the choice of objective dictates downstream task specialization.

Multi-modal large language models (MLLMs) have advanced general-purpose video understanding but struggle with long, high-resolution videos---they process every pixel equally in their vision transformers (ViTs) or LLMs despite significant spatiotemporal redundancy. We introduce AutoGaze, a lightweight module that removes redundant patches before processed by a ViT or an MLLM. Trained with next-token prediction and reinforcement learning, AutoGaze autoregressively selects a minimal set of multi-scale patches that reconstructs the video within a user-specified error threshold, eliminating redundancy while preserving information. Empirically, AutoGaze reduces visual tokens by 4x-100x and accelerates ViTs and MLLMs by up to 19x, scaling MLLMs to 1K-frame 4K-resolution videos and achieving superior results on video benchmarks (e.g., 67.0% on VideoMME). Furthermore, we introduce HLVid: the first high-resolution, long-form video QA benchmark with 5-minute 4K-resolution videos, where an MLLM scaled with AutoGaze improves over the baseline by 10.1% and outperforms the previous best MLLM by 4.5%. Project page: https://autogaze.github.io/.

Sign Language Production (SLP) aims to translate spoken language into sign sequences, where the main challenge lies in generating coherent and natural poses from discrete glosses (G2P). Existing G2P methods typically treat each pose as an indivisible unit, limiting their ability to capture fine-grained joint-level dependencies and thus degrading pose quality. To address this, we propose the Focal-General Diffusion Model (FGDM), characterized by a pioneering two-stage denoising framework that harmonizes local joint-level dependencies and global coherence. Specifically, in the Focal stage, a novel Adaptive Sign GCN (ASGCN) adaptively models each pose based on contextual correlations, skeletal topology, and semantic conditions, ensuring precise generation of local details. In the General stage, a Transformer-based module refines the entire pose sequence to enhance global coherence and naturalness. Moreover, we introduce a Semantic Consistent Guidance (SCG) mechanism that seamlessly integrates semantic supervision into diffusion training, enforcing tighter alignment between generated pose sequences and their intended gloss semantics. Extensive experiments on PHOENIX14T and USTC-CSL demonstrate that FGDM achieves SOTA performance. Our project page is available at https://yuyiheng-eu.github.io/fgdm/.

This paper introduces a novel unsupervised approach for image deblurring that utilizes a simple process for training data collection, thereby enhancing the applicability and effectiveness of deblurring methods. Our technique does not require meticulously paired data of blurred and corresponding sharp images; instead, it uses unpaired blurred and sharp images of similar scenes to generate pseudo-ground truth data by leveraging a dense matching model to identify correspondences between a blurry image and reference sharp images. Thanks to the simplicity of the training data collection process, our approach does not rely on existing paired training data or pre-trained networks, making it more adaptable to various scenarios and suitable for networks of different sizes, including those designed for low-resource devices. We demonstrate that this novel approach achieves state-of-the-art performance, marking a significant advancement in the field of image deblurring.

Pose-guided video generation refers to controlling the motion of subjects in generated video through a sequence of poses. It enables precise control over subject motion and has important applications in animation. However, current pose-guided video generation methods are limited to accepting only human poses as input, thus generalizing poorly to pose of other subjects. To address this issue, we propose PoseAnything, a general pose-guided video generation framework capable of handling both human and non-human characters, supporting arbitrary skeletal inputs. To enhance consistency preservation during motion, we introduce Part-aware Temporal Coherence Module, which divides the subject into different parts, establishes part correspondences, and computes cross-attention between corresponding parts across frames to achieve fine-grained part-level consistency. Additionally, we propose Subject and Camera Motion Decoupled CFG, a novel guidance strategy that, for the first time, enables independent camera movement control in pose-guided video generation, by separately injecting subject and camera motion control information into the positive and negative anchors of CFG. Furthermore, we present XPose, a high-quality public dataset containing 50,000 non-human pose-video pairs, along with an automated pipeline for annotation and filtering. Extensive experiments demonstrate that PoseAnything significantly outperforms state-of-the-art methods in both effectiveness and generalization.

Unified Multimodal Models (UMMs) have shown impressive performance in both understanding and generation with a single architecture. However, UMMs still exhibit a fundamental inconsistency: understanding favors compact embeddings, whereas generation favors reconstruction-rich representations. This structural trade-off produces misaligned decision boundaries, degraded cross-modal coherence, and heightened vulnerability under distributional and adversarial shifts. In this paper, we present UniGame, a self-adversarial post-training framework that directly targets the inconsistencies. By applying a lightweight perturber at the shared token interface, UniGame enables the generation branch to actively seek and challenge fragile understanding, turning the model itself into its own adversary. Experiments demonstrate that UniGame significantly improves the consistency (+4.6%). Moreover, it also achieves substantial improvements in understanding (+3.6%), generation (+0.02), out-of-distribution and adversarial robustness (+4.8% and +6.2% on NaturalBench and AdVQA). The framework is architecture-agnostic, introduces <1% additional parameters, and is complementary to existing post-training methods. These results position adversarial self-play as a general and effective principle for enhancing the coherence, stability, and unified competence of future multimodal foundation models.

Merging multiple Low-Rank Adaptation (LoRA) modules is promising for constructing general-purpose systems, yet challenging because LoRA update directions span different subspaces and contribute unevenly. When merged naively, such mismatches can weaken the directions most critical to certain task losses while overemphasizing relatively less important ones, ultimately reducing the model's ability to represent all tasks faithfully. We revisit this problem through two perspectives: subspace coverage, which captures how broadly LoRA directions cover diverse representational directions, and anisotropy, which reflects the imbalance of influence across those directions. We propose TARA-Merging (Task-Rank Anisotropy Alignment), which aligns merging weights using a preference-weighted cross-entropy pseudo-loss while preserving task-relevant LoRA subspaces. This ensures broad subspace coverage and mitigates anisotropy via direction-wise reweighting. Across eight vision and six NLI benchmarks, TARA-Merging consistently outperforms vanilla and LoRA-aware baselines, demonstrating strong robustness and generalization, and highlighting the importance of addressing both subspace coverage and anisotropy in LoRA merging.