CVPR 2026 Papers

Perceiving and reconstructing 3D scene geometry from visual inputs is crucial for autonomous driving. However, there still lacks a driving-targeted dense geometry perception model that can adapt to different scenarios and camera configurations. To bridge this gap, we propose a Driving Visual Geometry Transformer (DVGT), which reconstructs a global dense 3D point map from a sequence of unposed multi-view visual inputs. We first extract visual features for each image using a DINO backbone, and employ alternating intra-view local attention, cross-view spatial attention, and cross-frame temporal attention to infer geometric relations across images. We then use multiple heads to decode a global point map in the ego coordinate of the first frame and the ego poses for each frame. Unlike conventional methods that rely on precise camera parameters, DVGT is free of explicit 3D geometric priors, enabling flexible processing of arbitrary camera configurations. DVGT directly predicts metric-scaled geometry from image sequences, eliminating the need for post-alignment with external sensors. Trained on a large mixture of driving datasets including nuScenes, OpenScene, Waymo, KITTI, and DDAD, DVGT significantly outperforms existing models on various scenarios.

Graphical User Interface (GUI) Agents, benefiting from recent advances in multimodal large language models (MLLM), have achieved significant development. However, due to the frequent updates of GUI applications, adapting to new tasks without forgetting old tasks in GUI continual learning remains an open problem. In this work, we reveal that while Supervised Fine-Tuning (SFT) facilitates fast adaptation, it often triggers knowledge overwriting, whereas Reinforcement Learning (RL) demonstrates an inherent resilience that shields prior interaction logic from erasure. Based on this insight, we propose a Continual GUI Learning (CGL) framework that dynamically balances adaptation efficiency and skill retention by enhancing the synergy between SFT and RL. Specifically, we introduce an SFT proportion adjustment mechanism guided by policy entropy to dynamically control the weight allocation between the SFT and RL training phases. To resolve explicit gradient interference, we further develop a specialized gradient surgery strategy. By projecting exploratory SFT gradients onto GRPO-based anchor gradients, our method explicitly clips the components of SFT gradients that conflict with GRPO. On top of that, we establish an AndroidControl-CL benchmark, which divides GUI applications into distinct task groups to effectively simulate and evaluate the performance of continual GUI learning. Experimental results demonstrate the effectiveness of our proposed CGL framework across continual learning scenarios. The benchmark, code, and model will be made publicly available.

Recent advances in CLIP-based continual learning have shown the potential of leveraging pre-trained vision-language models for sequential tasks. However, existing methods overlook a key problem we call Asymmetric Drift. In unimodal CLIP-based continual learning, the visual branch undergoes stronger adaptation because the visual distribution shifts significantly, whereas the text branch remains relatively stable due to the low variance of textual prompts. This imbalance increases the modality distance and degrades cross-modal alignment over time. To address this issue, we propose CCA-CL, a framework that accumulates visual-textual covariance statistics across tasks and solves Canonical Correlation Analysis to compute a shared subspace. In this subspace, the distance between visual and textual features is minimized, enabling better alignment without modifying CLIP parameters. This also makes our method naturally compatible with exemplar-free CL settings. To further capture nonlinear relationships that linear Canonical Correlation Analysis is hard to model, we introduce Random Fourier Projection as an extension. Experimental results demonstrate that CCA-CL effectively mitigates the asymmetric drift problem and achieves state-of-the-art performance on several benchmarks.

Counting is a core capability for multimodal large language models (MLLMs), yet there is no unified counting dataset to rigorously evaluate this ability across image, text, and audio. We present UNICBench, a unified multimodal, multi-level counting benchmark and evaluation toolkit with accurate ground truth, deterministic numeric parsing, and stratified reporting. The corpus comprises 5,300 images (5,508 QA), 872 documents (5,888 QA), and 2,069 audio clips (2,905 QA), annotated with a three-level capability taxonomy and difficulty tags. Under a standardized protocol with fixed splits/prompts/seeds and modality-specific matching rules, we evaluate 45 state-of-the-art MLLMs across modalities. Results show strong performance on some basic counting tasks but significant gaps on reasoning and the hardest partitions, highlighting long-tail errors and substantial headroom for improving general counting. UNICBench offers a rigorous and comparable basis for measurement and a public toolkit to accelerate progress.

This paper introduces a novel framework for wide-angle correction by distilling the geometric principles of quasi-conformal (QC) mapping into a generalizable and efficient deep neural network. Our methodology can be divided into two primary stages. In the first stage, we develop an annotation-free teacher pipeline that treats the distortion correction problem as a QC mapping task. Specifically, we minimize the Beltrami smoothness energy under constraints of both line structures and human body regions using a Linear Beltrami Solver and Proximal Gradient Descent (LBS-PGD) algorithm, thereby automatically generating high-quality QC correction flow labels. In the second stage, we propose the Quasi-conformal-mapping Distilled Wide-angle Correction Network (QDWC-Net) to learn the geometric transformation from these labels via distillation. Utilizing a Mamba-based backbone, a soft-argmin head, and a low-rank prior reconstruction module, QDWC-Net predicts the correction flow directly from a distorted input. Extensive quantitative and qualitative experiments verify the effectiveness of our approach. Notably, our distilled student network exhibits enhanced robustness compared to the teacher and achieves a massive 32x speedup (from 26.33s to 0.81s). Overall, our method provides a state-of-the-art solution that excels across multiple real-world datasets, especially in mitigating human body distortion.

The vulnerability of deep neural networks to adversarial examples poses a significant challenge for real-world deployment. Existing techniques to enhance deep network robustness rely on adversarial training, an approach that is powerful but computationally intensive and typically tailored to specific attack types. To address these limitations, existing works have explored techniques such as adding gaussian noise or filtering images, both of which can boost the network robustness to various adversarial attacks, albeit modestly. Here, we theoretically demonstrate that these two approaches enhance robustness against adversarial attacks through complementary mechanisms, resulting in supralinear robustness when combined.Building on this insight, we experimentally show that a simple preprocessor combining Gaussian noise and bilateral filtering yields supralinear improvements in adversarial robustness with minimal computational cost. Next, we combine our preprocessor with adversarial training and test on RobustBench to assess its supralinear improvement over state-of-the-art defenses. First, this combination ranks second on AutoAttack and third overall, while using only ~35% of the training FLOPs, using a model with 50% less parametets, trained with ~33% of the epochs and ~15% the data compared to state-of-the-art defenses. Second, our method scales efficiently, matching the accuracy of competing models with roughly 2-8x less total compute across ~3 orders of magnitude. Overall, our approach provides a principled and easily integrable framework for enhancing adversarial robustness, offering negligible computational overhead and a simple yet theoretically grounded design.

Conventional multi-projector calibration requires projecting and capturing structured light patterns for each projector sequentially, causing calibration time and effort to increase linearly with the number of projectors. This scalability bottleneck has long limited the deployment of large-scale projection mapping systems. We present a new calibration framework that breaks this limitation by embedding cameras into the surface of the calibration target. The embedded cameras directly capture the incoming projection light, enabling the separation of simultaneously projected structured light patterns from multiple projectors according to their incident directions. Our method establishes correspondences between the optical centers of the embedded cameras and the projector pixels, allowing the intrinsic and extrinsic parameters of all projectors to be simultaneously estimated. We further introduce a correction technique for small misalignments between the calibration board and camera optical centers. As a result, our system achieves calibration accuracy comparable to conventional methods while reducing the required number of projection-capture cycles from linear to nearly constant with respect to the number of projectors, dramatically improving scalability for dense multi-projector systems with overlapping projection regions, such as high-brightness stacking, super-resolution, light-field, and shadow-suppression displays.

Embodied navigation is a fundamental capability for robotic agents operating. Real-world deployment requires open vocabulary generalization and low training overhead, motivating zero-shot methods rather than task-specific RL training. However, existing zero-shot methods that build explicit 3D scene graphs often compress rich visual observations into text-only relations, leading to high construction cost, irreversible loss of visual evidence, and constrained vocabularies.To address these limitations, we introduce the Multi-modal 3D Scene Graph (M3DSG), which preserves visual cues by replacing textual relational edges with dynamically assigned images. Built on M3DSG, we propose MSGNav, a zero-shot navigation system that includes a Key Subgraph Selection module for efficient reasoning, an Adaptive Vocabulary Update module for open vocabulary support, and a Closed-Loop Reasoning module for accurate exploration reasoning. Additionally, we further identify the "last mile" problem in zero-shot navigation -- determining the feasible target location with a suitable final viewpoint, and propose a Visibility-based Viewpoint Decision module to explicitly resolve it. Comprehensive experimental results demonstrate that MSGNav achieves state-of-the-art performance on GOAT-Bench and HM3D-OVON datasets. The open-source code will be publicly available.

Recent advances in pretraining 3D point cloud encoders (e.g., Point-BERT, Point-MAE) have produced powerful models, whose abilities are typically evaluated on geometric or semantic tasks. At the same time, topological descriptors have been shown to provide informative summaries of a shape's multiscale structure. In this paper we pose the question whether topological information can be derived from features produced by 3D encoders. To address this question, we first introduce DONUT, a synthetic benchmark with controlled topological complexity, and propose FILTR (Filtration Transformer), a learnable framework to predict persistence diagrams directly from frozen encoders. FILTR adapts a transformer decoder to treat diagram generation as a set prediction task. Our analysis on DONUT reveals that existing encoders retain only limited global topological signals, yet FILTR successfully leverages information produced by these encoders to approximate persistence diagrams. Our approach enables, for the first time, data-driven extraction of persistence diagrams from raw point clouds through an efficient learnable feed-forward mechanism.

Generating realistic and physically plausible 3D Human-Object Interactions (HOI) remains a key challenge in motion generation. One primary reason is that describing these physical constraints with words alone is difficult. To address this limitation, we propose a new paradigm: extracting rich interaction priors from easily accessible 2D images. Specifically, we introduce ViHOI, a novel framework that enables diffusion-based generative models to leverage rich, task-specific priors from 2D images to enhance generation quality. We utilize a large Vision-Language Model (VLM) as a powerful prior-extraction engine and adopt a layer-decoupled strategy to obtain visual and textual priors. Concurrently, we design a Q-Former-based adapter that compresses the VLM's high-dimensional features into compact prior tokens, which significantly facilitates the conditional training of our diffusion model. Our framework is trained on motion-rendered images from the dataset to ensure strict semantic alignment between visual inputs and motion sequences. During inference, it leverages reference images synthesized by a text-to-image generation model to improve generalization to unseen objects and interaction categories. Experimental results demonstrate that ViHOI achieves state-of-the-art performance, outperforming existing methods across multiple benchmarks and demonstrating superior generalization. The code for this work will be released at https//github.com/MPI-Lab/ViHOI.

This paper presents GeoAgent, a model capable of reasoning closely with humans and deriving fine-grained address conclusions. Previous RL-based methods have achieved breakthroughs in performance and interpretability but still remain concerns because of their reliance on AI-generated chain-of-thought (CoT) data and training strategies, which conflict with geographic characteristics. To address these issues, we first introduce GeoSeek, a new geolocation dataset comprising CoT data annotated by geographic experts and professional players. We further thoroughly explore the inherent characteristics of geographic tasks and propose a geo-similarity reward and a consistency reward assessed by a consistency agent to assist training. This encourages the model to converge towards correct answers from a geographic perspective while ensuring the integrity and consistency of its reasoning process. Experimental results show that GeoAgent outperforms existing methods and a series of general VLLMs across multiple grains, while generating reasoning that closely aligns with humans. Pretrained model and data will be openly available.

With the rapid development of pre-training technologies, adapting large-scale Vision-Language Models (VLMs) for video understanding i.e. image-to-video transfer learning has become a dominant paradigm. To achieve superior performance, it raises as an effective strategy among recent advances to employ Mixture-of-Experts (MoE) to enhance VLMs' temporal modeling capabilities. However, conventional MoE designs suffer from expert homogenization, where all experts act as identical generalists, inefficiently learning spatio-temporal features from undifferentiated video streams.To overcome this problem, we propose VidPrism, a novel heterogeneous temporal Mixture-of-Experts framework. VidPrism pioneers a division of labor by deploying functionally specialized experts, each assuming a role ranging from spatial understanding to temporal modeling.To feed these specialists appropriately, we introduce a content-aware, multi-rate sampling module that dynamically generates streams ranging from semantically rich to motion-focused representations, providing specialized inputs for experts.Furthermore, a dynamic, bidirectional fusion mechanism enables synergistic information exchange between these pathways, leading to a comprehensive video representation. Extensive experiments on various video recognition benchmarks demonstrate that VidPrism achieves state-of-the-art performance and effectively fosters expert specialization.

Few-step generation has been a long-standing goal, with recent one-step generation methods exemplified by MeanFlow achieving remarkable results. Existing research on MeanFlow primarily focuses on class-to-image generation. However, an intuitive yet unexplored direction is to extend the condition from fixed class labels to flexible text inputs, enabling richer content creation. Compared to the limited class labels, text conditions pose greater challenges to the model's understanding capability, necessitating the effective integration of powerful text encoders into the MeanFlow framework. Surprisingly, although incorporating text conditions appears straightforward, we find that integrating powerful LLM-based text encoders using conventional training strategies results in unsatisfactory performance. To uncover the underlying cause, we conduct detailed analyses and reveal that, due to the extremely limited number of refinement steps in the MeanFlow generation, such as only one step, the text feature representations are required to possess sufficiently high discriminability. This also explains why discrete and easily distinguishable class features perform well within the MeanFlow framework. Guided by these insights, we leverage a powerful LLM-based text encoder validated to possess the required semantic properties and adapt the MeanFlow generation process to this framework, resulting in efficient text-conditioned synthesis for the first time. Furthermore, we validate our approach on the widely used diffusion model, demonstrating significant generation performance improvements. We hope this work provides a general and practical reference for future research on text-conditioned MeanFlow generation. The code is available at \supp https://github.com/AMAP-ML/EMF.

Novel view synthesis of dynamic scenes is fundamental to achieving photorealistic 4D reconstruction and immersive visual experiences. Recent progress in Gaussian-based representations has significantly improved real-time rendering quality, yet existing methods still struggle to maintain a balance between long-term static and short-term dynamic regions in both representation and optimization. To address this, we present SharpTimeGS, a lifespan-aware 4D Gaussian framework that achieves temporally adaptive modeling of both static and dynamic regions under a unified representation. Specifically, we introduce a learnable lifespan parameter that reformulates temporal visibility from a Gaussian-shaped decay into a flat-top profile, allowing primitives to remain consistently active over their intended duration and avoiding redundant densification. In addition, the learned lifespan modulates each primitive's motion, reducing drift in long-lived static points while retaining unrestricted motion for short-lived dynamic ones. This effectively decouples motion magnitude from temporal duration, improving long-term stability without compromising dynamic fidelity. Moreover, we design a lifespan-velocity-aware densification strategy that mitigates optimization imbalance between static and dynamic regions by allocating more capacity to regions with pronounced motion while keeping static areas compact and stable. Extensive experiments on multiple benchmarks demonstrate that our method achieves state-of-the-art performance while supporting real-time rendering up to 4K resolution at 100 FPS on one RTX 4090.

Multi-view image compression (MIC) aims to achieve high compression efficiency by exploiting inter-image correlations, playing a crucial role in 3D applications. As a subfield of MIC, distributed multi-view image compression (DMIC) offers performance comparable to MIC while eliminating the need for inter-view information at the encoder side.However, existing methods in DMIC typically treat all images equally, overlooking the varying degrees of correlation between different views during decoding, which leads to suboptimal coding performance. To address this limitation, we propose a novel OmniParallax Attention Mechanism (OPAM), which is a general mechanism for explicitly modeling correlations and aligned features between arbitrary pairs of information sources.Building upon OPAM, we propose a Parallax Multi Information Fusion Module (PMIFM) to adaptively integrate information from different sources. PMIFM is incorporated into both the joint decoder and the entropy model to construct our end-to-end DMIC framework, ParaHydra.Extensive experiments demonstrate that ParaHydra is the first DMIC method to significantly surpass state-of-the-art MIC codecs, while maintaining low computational overhead. Performance gains become more pronounced as the number of input views increases. Compared with LDMIC, ParaHydra achieves bitrate savings of 19.72\% on WildTrack(3) and up to 24.18\% on WildTrack(6), while significantly improving coding efficiency (as much as 65xin decoding and 34xin encoding).

Multimodal Web Search Agents demonstrate a practically valuable capability by fusing information from diverse modalities (e.g., text and vision), retrieved iteratively from the internet, to address complex user queries. However, the visual modality is prone to information overload, and the noise contained within it--such as irrelevant background details or complex structures--can disrupt the model's attention, misdirecting its operational focus toward an erroneous path. To address the aforementioned challenge, we propose ReFAct (Reasoning, Focusing, and Acting), a novel framework that empowers the agent to actively manage its cross-modal context. This allows the agent to adjust its operational focus, thereby mitigating the impact of noise on multimodal Web Search Agents. Specifically, ReFAct employs a Grounding tool for active visual perception to dynamically filter information. We also design external memory-based Defocus/Refocus operations for selective information retention, further modulating information density within the multimodal context. Ultimately, this ensures the agent maintains focus during problem-solving. To evaluate and enhance agent capabilities in complex and noisy multimodal contexts, we first propose a pipeline for constructing datasets with flexible complexity. We introduce a new open-source benchmark: GroundedVQA. Finally, we experimentally demonstrate the effectiveness of our proposed method on GroundedVQA and other widely-used benchmarks.

Deep neural networks are highly vulnerable to adversarial examples, i.e.,small perturbations that can significantly degrade model performance. While adversarial training has become the primary defense strategy, most studies focus on balanced datasets, overlooking the challenges posed by real-world long-tail data. Motivated by the fact that perturbations in adversarial examples inherently alter the training distribution, we theoretically investigate their impact. We first revisit adversarial training for long-tail data and identify two key limitations: (i) a skewed training objective caused by class imbalance, and (ii) unstable evolution of adversarial distributions. Furthermore, we show that perturbations can simultaneously address both adversarial vulnerability and class imbalance. Based on these insights, we propose \METHODNAME , a plug-and-play framework that adaptively adjusts perturbations during adversarial training. Extensive experiments demonstrate that \METHODNAME consistently enhances adversarial robustness and class-balance on long-tailed datasets. The code is available at \href https://github.com/zhang-lilin/RobustLT https://github.com/zhang-lilin/RobustLT .

Chain-of-thought (CoT) reasoning has emerged as a powerful tool for multimodal large language models on video understanding tasks. However, its necessity and advantages over direct answering remain underexplored. In this paper, we first demonstrate that for RL-trained video models, direct answering often matches or even surpasses CoT performance, despite CoT producing step-by-step analyses at a higher computational cost. Motivated by this, we propose VideoAuto-R1, a video understanding framework that adopts a reason-when-necessary strategy. During training, our approach follows a Thinking Once, Answering Twice paradigm: the model first generates an initial answer, then performs reasoning, and finally outputs a reviewed answer. Both answers are supervised via verifiable rewards. During inference, the model uses the confidence score of the initial answer to determine whether to proceed with reasoning. Across video QA and grounding benchmarks, VideoAuto-R1 achieves state-of-the-art accuracy with significantly improved efficiency, reducing the average response length by 3.3x, eg., from 149 to just 44 tokens. Moreover, we observe a low rate of thinking-mode activation on perception-oriented tasks, but a higher rate on reasoning-intensive tasks. This suggests that explicit language-based reasoning is generally beneficial but not always necessary.

Deep learning-based gaze estimation methods tend to suffer from substantial performance drop in real-world scenarios with varying users and environments. To tackle this issue, most recent approaches employ Unsupervised Domain Adaptation (UDA) to bridge the gap between source and target domains. However, this paradigm is misaligned with real-world scenarios, where the system typically needs to adapt to only a single new user. Therefore, this paper advocates a more practical paradigm: Unsupervised Personal Adaptation (UPA), which calibrates a pre-trained model using a few unlabeled images from a single new user. Conventional UDA methods do not guarantee improvements for every user and often yield lower average performance in this setting. To address this problem, we propose Render-to-Adapt (R2A), a self-supervised framework specifically designed for the UPA task. Given a pretrained gaze model, R2A utilizes a gaze-conditioned renderer to synthesize new images based on the model's gaze predictions, and enforces eye-region consistency as a label-free signal to enhance personalized gaze estimation. We evaluate R2A on a re-designed cross-dataset personal adaptation benchmark. Experimental results show that R2A consistently improves performance across all individuals and significantly outperforms existing SOTA methods.