Reasoning-Driven Amodal Completion: Collaborative Agents and Perceptual Evaluation
School of Computer Science and Engineering, Beihang University（计算机科学与工程学院，北京航空航天大学）；School of Software, Beihang University（软件学院，北京航空航天大学）；School of Computing and Information Systems, The University of Melbourne（计算与信息系统学院，墨尔本大学）
Amodal completion, the task of inferring invisible object parts, faces significant challenges in maintaining semantic consistency and structural integrity. Prior progressive approaches are inherently limited by inference instability and error accumulation. To tackle these limitations, we present a Collaborative Multi-Agent Reasoning Framework that explicitly decouples Semantic Planning from Visual Synthesis. By employing specialized agents for upfront reasoning, our method generates a structured, explicit plan before pixel generation, enabling visually and semantically coherent single-pass synthesis. We integrate this framework with two critical mechanisms: (1) a self-correcting Verification Agent that employs Chain-of-Thought reasoning to rectify visible region segmentation and identify residual occluders strictly within the Semantic Planning phase, and (2) a Diverse Hypothesis Generator that addresses the ambiguity of invisible regions by offering diverse, plausible semantic interpretations, surpassing the limited pixel-level variations of standard random seed sampling. Furthermore, addressing the limitations of traditional metrics in assessing inferred invisible content, we introduce the MAC-Score (MLLM Amodal Completion Score), a novel human-aligned evaluation metric. Validated against human judgment and ground truth, these metrics establish a robust standard for assessing structural completeness and semantic consistency with visible context. Extensive experiments demonstrate that our framework significantly outperforms state-of-the-art methods across multiple datasets. Our project is available at: https://fanhongxing.github.io/remac-page.
Universitat Pompeu Fabra (UPF)（庞培法布拉大学）；Centre de Visió per Computador (CVC)（计算机视觉中心）；DxO Labs（DxO实验室）
This paper presents a computational model to recover the most likely interpretation of the 3D scene structure from a planar image, where some objects may occlude others. The estimated scene interpretation is obtained by integrating some global and local cues and provides both the complete disoccluded objects that form the scene and their ordering according to depth. Our method first computes several distal scenes which are compatible with the proximal planar image. To compute these different hypothesized scenes, we propose a perceptually inspired object disocclusion method, which works by mini…
HUPE: Heuristic Underwater Perceptual Enhancement with Semantic Collaborative Learning
School of Software Engineering, Dalian University of Technology（大连理工大学软件学院）；College of Information Science and Technology, Dalian Maritime University（大连海事大学信息科学技术学院）；Pazhou Laboratory (Huangpu)（琶洲实验室（黄埔））
Cooperative Medianet Innovation Center, Shanghai Jiao Tong University（上海交通大学合作媒体网络创新中心）；University of Southern California（南加州大学）；Shanghai Jiao Tong University（上海交通大学）；Shanghai AI Laboratory（上海人工智能实验室）
Multi-agent collaborative perception could significantly upgrade the perception performance by enabling agents to share complementary information with each other through communication. It inevitably results in a fundamental trade-off between perception performance and communication bandwidth. To tackle this bottleneck issue, we propose a spatial confidence map, which reflects the spatial heterogeneity of perceptual information. It empowers agents to only share spatially sparse, yet perceptually critical information, contributing to where to communicate. Based on this novel spatial confidence m…
Visual Para-Thinker++: A Single-Policy Multi-Agent Framework for Visual Reasoning
Zhejiang University（浙江大学）；Hunan University（湖南大学）；Tianjin University（天津大学）；University of Chinese Academy of Sciences（中国科学院大学）；Shanghai Jiao Tong University（上海交通大学）；Jilin University（吉林大学）
Dual-Latent Collaborative Decoding for Fidelity-Perception Balanced Image Compression
School of Information and Communication Engineering and the State Key Laboratory of Media Convergence and Communication, Communication University of China（信息与通信工程学院和媒体融合与通信国家重点实验室，中国通信大学）；School of Information Science and Electronic Engineering, Shanghai Jiao Tong University（信息科学与电子工程学院，上海交通大学）；Department of Computer Science, City University of Hong Kong（计算机科学系，香港城市大学）；State Key Laboratory of Multimedia information Processing, School of Computer Science, Peking University（多媒体信息处理国家重点实验室，计算机科学学院，北京大学）
AutoGUI-v2: A Comprehensive Multi-Modal GUI Functionality Understanding Benchmark
University of Chinese Academy of Sciences（中国科学院大学）；New Laboratory of Pattern Recognition（模式识别新实验室）；State Key Laboratory of Multimodal Artificial Intelligence Systems（多模态人工智能系统国家重点实验室）；Hong Kong Institute of Science & Innovation（香港科学创新研究院）；PolyU；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
Weakly supervised object detection has recently received much attention, since it only requires image-level labels instead of the bounding-box labels consumed in strongly supervised learning. Nevertheless, the save in labeling expense is usually at the cost of model accuracy. In this paper, we propose a simple but effective weakly supervised collaborative learning framework to resolve this problem, which trains a weakly supervised learner and a strongly supervised learner jointly by enforcing partial feature sharing and prediction consistency. For object detection, taking WSDDN-like architectu…
CERF: Communication-Efficient and Retraining-Free Collaborative Perception
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
CATNet: Collaborative Alignment and Transformation Network for Cooperative Perception
School of Computer Science and Technology, Tianjin University（计算机科学与技术学院，天津大学）；School of Cybersecurity, Tianjin University（网络安全学院，天津大学）；School of Future Technology, Tianjin University（未来技术学院，天津大学）
Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue
College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China（复旦大学计算机科学与人工智能学院）；Shanghai Innovation Institute, Shanghai, China（上海创新研究院）；Mechanical Systems Control Lab, UC Berkeley, California, USA（伯克利机械系统控制实验室）
Shanghai Jiao Tong University（上海交通大学）；Shanghai AI Laboratory（上海人工智能实验室）
Collaborative perception has recently shown great potential to improve perception capabilities over single-agent perception. Existing collaborative perception methods usually consider an ideal communication environment. However, in practice, the communication system inevitably suffers from latency issues, causing potential performance degradation and high risks in safety-critical applications, such as autonomous driving. To mitigate the effect caused by the inevitable latency, from a machine learning perspective, we present the first latency-aware collaborative perception system, which activel…
CoLC: Communication-Efficient Collaborative Perception with LiDAR Completion
Key Laboratory of Big Data & Artificial Intelligence in Transportation, Ministry of Education（交通运输大数据与人工智能重点实验室，教育部）；School of Computer Science and Technology, Beijing Jiaotong University（北京交通大学计算机科学与技术学院）；Xiamen University（厦门大学）
CoBEVMoE: Heterogeneity-aware Feature Fusion with Dynamic Mixture-of-Experts for Collaborative Perception
School of Computer Science and Electronic Engineering, Hunan University（计算机科学与电子工程学院，湖南大学）；School of Artificial Intelligence and Robotics, Hunan University（人工智能与机器人学院，湖南大学）；National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University（机器人视觉感知与控制技术国家工程研究中心，湖南大学）
