Du, Chenxi, Deng, Yongheng, Liu, Jiani, Zhang, Yujia, Chen, Xi, Ren, Ju
Large Multimodal Models (LMMs) have shown remarkable success in visual understanding tasks. LMMs encode visual and textual inputs into tokens, which are then processed by Large Language Models (LLMs). However, the large number of visual tokens poses a major bottleneck for inference efficiency and memory usage. Reducing visual tokens is a promising training-free solution, but existing methods remain limited. Importance-based approaches suffer from poor generalization, are incompatible with kernel-level inference optimizations, and only consider information from a single modality. Diversity-based strategies typically focus on pairwise token redundancy and treat all tokens as equally important. Recent attempts to sequentially combine importance and diversity criteria still fail to address the intrinsic drawbacks of their underlying metrics. To address these limitations, we reformulate visual token reduction as an optimal subset selection problem jointly guided by two complementary objectives: informativeness and coverage. Informativeness is quantified through per-token intrinsic saliency and visual-textual alignment, while coverage is enforced via a volume-based subset selection criterion that ensures global representativeness in the visual feature space. This joint formulation effectively integrates visual saliency, cross-modal alignment, and global coverage in an end-to-end token selection process, yielding a computationally efficient, model-agnostic framework compatible with modern inference accelerators. Extensive experiments demonstrate that CoIn substantially reduces computation and memory cost while maintaining strong task performance.
尚无 AI 解读，展示原文摘要
cs.CV · cs.CL
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表
Omnimodal large language models (OmniLLMs) have attracted increasing research attention of late towards unified audio-video understanding. However, the high computational cost of processing longer joint audio-video token sequences has become a key bottleneck. Existing token compression methods have not addressed the emerging need to jointly compress multimodal tokens. To bridge this gap, we present OmniZip, a training-free, audio-guided audio-visual token-compression framework that optimizes multimodal token representation and accelerates model inference. Specifically, OmniZip first identifies salient audio tokens, then computes an audio retention score for each time group to capture information density, thereby dynamically guiding video token pruning and preserving cues from audio anchors enhanced by cross-modal similarity. For each time window, OmniZip compresses the video tokens using an interleaved spatio-temporal scheme. Extensive results demonstrate the merits of OmniZip: it achieves a 3.42x inference speedup and a 1.4x memory reduction over other top-performing counterparts, while maintaining the performance of OmniLLMs without training.
尚无 AI 解读，展示原文摘要
cs.CV · cs.CL
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表
Video agentic models have advanced challenging video-language tasks. However, most agentic approaches still heavily rely on greedy parsing over densely sampled video frames, resulting in high computational cost. We present VideoSeek, a long-horizon video agent that leverages video logic flow to actively seek answer-critical evidence instead of exhaustively parsing the full video. This insight allows the model to use far fewer frames while maintaining, or even improving, its video understanding capability. VideoSeek operates in a think-act-observe loop with a well-designed toolkit for collecting multi-granular video observations. This design enables query-aware exploration over accumulated observations and supports practical video understanding and reasoning. Experiments on four challenging video understanding and reasoning benchmarks demonstrate that VideoSeek achieves strong accuracy while using far fewer frames than prior video agents and standalone LMMs. Notably, VideoSeek achieves a 10.2 absolute points improvement on LVBench over its base model, GPT-5, while using 93% fewer frames. Further analysis highlights the significance of leveraging video logic flow, strong reasoning capability, and the complementary roles of toolkit design.
尚无 AI 解读，展示原文摘要
cs.CV · cs.AI
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表
4D millimeter-wave radar is a promising sensing modality for autonomous driving, yet effective 3D object detection from 4D radar and monocular images remains challenging. Existing fusion approaches either rely on instance proposals lacking global context or dense BEV grids constrained by rigid structures, lacking a flexible and adaptive representation for diverse scenes. To address this, we propose RaGS, the first framework that models the scene as a continuous field of Gaussians, enabling dynamic resource allocation to foreground objects detection while maintaining flexibility and efficiency. Specifically, RaGS adopts a cascaded pipeline to construct and progressively refine the Gaussian field. It begins with Frustum-based Localization Initiation (FLI), which unprojects foreground pixels to initialize coarse Gaussian centers. Then, Iterative Multimodal Aggregation (IMA) explicitly exploits image semantics and implicitly integrates 4D radar velocity geometry to refine the Gaussians within regions of interest. Finally, Multi-level Gaussian Fusion (MGF) renders the Gaussian field into hierarchical BEV features for 3D object detection. By dynamically focusing on sparse and informative regions, RaGS achieves object-centric precision and comprehensive scene perception. Extensive experiments on View-of-Delft, TJ4DRadSet, and OmniHD-Scenes demonstrate its robustness and SOTA performance. Source code is available at https://github.com/shawnnnkb/RaGS.
尚无 AI 解读，展示原文摘要
cs.CV
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表
Training Large Multimodality Models (LMMs) relies on descriptive image caption that connects image and language. Existing methods for generating such captions often rely on distilling the captions from pretrained LMMs, constructing them from publicly available internet images, or even generating them through human annotation. However, these strategies can fall short in terms of precision and granularity, particularly when dealing with complex visual reasoning tasks. In this paper, we propose to leverage off-the-shelf visual specialists, which were trained from annotated images initially not for image captioning, for enhancing the image caption. Our approach, named Cap-Workflow, explores object low-level and fine-grained attributes (e.g., depth, emotion and fine-grained categories) and object relations (e.g., relative location and human-object-interaction (HOI)), and combine the attributes into the descriptive caption. By systematically integrating these rich attributes into the generated captions, Cap-Workflow significantly improves the descriptive quality of the captions, providing a deeper and more nuanced understanding of the visual content. Experiments demonstrate that such visual specialists are able to improve the performance for visual understanding tasks as well as reasoning that benefits from more accurate visual understanding. The source code and datasets are available at https://github.com/syp2ysy/Cap-Workflow.
尚无 AI 解读，展示原文摘要
cs.CV
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表
The rapid advancement of generative AI enables the creation of highly realistic text images, posing significant security risks from fraud and disinformation. However, research into robust detection is critically hampered by existing datasets that lack scale, diversity, and updated counterfeit techniques, as well as by models that fail to generalize. To address these deficiencies, we introduce DanceText, a large-scale, comprehensive dataset for AI-counterfeited text image detection. Constructed using our novel Creative Proposer pipeline, which automates the generation of diverse and realistic counterfeits, DanceText surpasses previous works by over 100-fold in multiple dimensions. It is the first to include counterfeits from multimodal large models, commercial software, and mobile apps, covering all major paradigms, including full-image generation, regional removal, and editing. Building on this dataset, we propose DS-Net, a novel and effective detection model. It features two key components: a Forensic Decoupling Encoder to extract generator-agnostic artifact features, and a Synergy Denoising Decoder that synergizes image-level classification with instance-level localization. Extensive experiments demonstrate that DS-Net achieves state-of-the-art performance, advancing the field toward robust and unified detection of AI-counterfeited text images in real-world scenarios. Both our code and dataset will be released publicly.
尚无 AI 解读，展示原文摘要
cs.CV
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表
Accurate depth estimation is crucial for 3D reconstruction and precise navigation in posterior segment ophthalmic surgery. However, acquiring annotated data remains challenging due to the impracticality of depth sensors under surgical microscopes. To overcome this limitation, we introduce RetinalDepth, a novel synthetic dataset comprising 44,800 temporal stereo image pairs across 896 diverse scenes for posterior segment surgery, developed via a Real2Sim2Real pipeline. In the Real-to-Sim phase, we model anatomically accurate eyes and instruments in Blender, integrating ultra-wide-field retinal textures, refractive aqueous humor, and dynamic trajectories, enhanced by post-processing for realism. RetinalDepth provides synchronized left and right RGB frames with pixel-perfect depth maps, surface normals, instrument segmentation masks, and camera parameters, enabling robust training of monocular, stereo, and video depth estimation models. In the Sim-to-Real phase, we introduce temporal depth variance, a novel metric for quantifying the stability of frame-to-frame depth estimation. Fine-tuning on RetinalDepth significantly boosts model performance on both synthetic and real surgical videos, enhancing generalization, surgical precision, and novice training. As the first synthetic benchmark for posterior segment surgery, RetinalDepth bridges the sim-to-real gap in ophthalmic computer vision.
尚无 AI 解读，展示原文摘要
cs.CV
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表
Reinforcement learning (RL) has demonstrated remarkable success in text and image generation, yet its potential in 3D generation remains largely unexplored. Existing attempts typically rely on offline direct preference optimization (DPO) method, which suffers from low training efficiency and limited generalization. In this work, we aim to enhance both the training efficiency and generation quality of RL in 3D mesh generation. Specifically, (1) we design the first asynchronous online RL framework tailored for 3D mesh generation post-training efficiency improvement, which is 3.75xfaster than synchronous RL. (2) We propose Advantage-guided Ranking Preference Optimization (ARPO), a novel RL algorithm that achieves a better trade-off between training efficiency and generalization than current RL algorithms designed for 3D mesh generation, such as DPO and group relative policy optimization (GRPO). (3) Based on asynchronous ARPO, we propose Mesh-Pro, which additionally introduces a novel diagonal-aware mixed triangular-quadrilateral tokenization for mesh representation and a ray-based reward for geometric integrity. Mesh-Pro achieves state-of-the-art performance on artistic and dense meshes.
尚无 AI 解读，展示原文摘要
cs.CV
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表