3D 视觉

Decentralized Nonlinear Model Predictive Control-Based Flock Navigation with Real-Time Obstacle Avoidance in Unknown Obstructed Environments

Nuthasith Gerdpratoom, Kaoru Yamamoto

专题命中 点云 ：point cloud(abstract)；分类 cs.RO

Comments 22 pages, 14 figures, to be published in Frontiers in Robotics and AI

Journal ref Frontiers in Robotics and AI, Vol. 12, 2025

Pathfinder for Low-altitude Aircraft with Binary Neural Network

Kaijie Yin, Tian Gao, Hui Kong

机构 * University of Macau（澳门大学） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV

Hierarchical Abstraction Enables Human-Like 3D Object Recognition in Deep Learning Models

Shuhao Fu, Philip J. Kellman, Hongjing Lu

专题命中 点云 ：point cloud(abstract)；分类 cs.CV

Journal ref In: Proceedings of the 47th Annual Meeting of the Cognitive Science Society, 2025

DLBAcalib: Robust Extrinsic Calibration for Non-Overlapping LiDARs Based on Dual LBA

Han Ye, Yuqiang Jin, Jinyuan Liu, Tao Li, Wen-An Zhang, Minglei Fu

机构 * Department of Information Engineering, Zhejiang University of Technology（浙江工业大学信息工程学院） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.RO

Comments 9 pages,14 figures

A Novel Streamline-based diffusion MRI Tractography Registration Method with Probabilistic Keypoint Detection

Junyi Wang, Mubai Du, Ye Wu, Yijie Li, William M. Wells, Lauren J. O'Donnell, Fan Zhang

机构 * University of Electronic Science and Technology of China（电子科技大学） ； Nanjing University of Science and Technology（南京理工大学） ； Harvard Medical School（哈佛医学院） ； Brigham and Women’s Hospital（布莱根和妇女医院） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV

3D forest semantic segmentation using multispectral LiDAR and 3D deep learning

Narges Takhtkeshha, Lauris Bocaux, Lassi Ruoppa, Fabio Remondino, Gottfried Mandlburger, Antero Kukko, Juha Hyyppä

专题命中 点云 ：point cloud(abstract)；分类 cs.CV

SP$^2$T: Sparse Proxy Attention for Dual-stream Point Transformer

Jiaxu Wan, Hong Zhang, Ziqi He, Yangyan Deng, Qishu Wang, Ding Yuan, Yifan Yang

机构 * School of Aerospace, BUAA（航空学院） ； School of Artificial Intelligence, BUAA（人工智能学院） ； School of Electronics and Information Engineering, BUAA（电子与信息工程学院） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV

Comments Accept by ICCV2025

Towards High-Resolution 3D Anomaly Detection: A Scalable Dataset and Real-Time Framework for Subtle Industrial Defects

Yuqi Cheng, Yihan Sun, Hui Zhang, Weiming Shen, Yunkang Cao

专题命中 点云 ：point cloud(abstract)；分类 cs.CV

Comments 14 pages, 8figures

HyperGCT: A Dynamic Hyper-GNN-Learned Geometric Constraint for 3D Registration

Xiyu Zhang, Jiayi Ma, Jianwei Guo, Wei Hu, Zhaoshuai Qi, Fei Hui, Jiaqi Yang, Yanning Zhang

机构 * Northwestern Polytechnical University（北华理工大学） ； Wuhan University（武汉大学） ； Chinese Academy of Sciences（中国科学院） ； Peking University（北京大学） ； Chang’an University（长安大学） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV

Comments Accepted to ICCV 2025

VectorLLM: Human-like Extraction of Structured Building Contours vis Multimodal LLMs

Tao Zhang, Shiqing Wei, Shihao Chen, Wenling Yu, Muying Luo, Shunping Ji

机构 * School of Remote Sensing and Information Engineering（遥感与信息工程学院） ； College of Oceanography and Space Informatics（海洋学与空间信息学院） ； School of Surveying and Geoinformation Engineering（测绘与地理信息工程学院） 纠错

专题命中 点云 ：spatial understanding(abstract)；分类 cs.CV

PRISM: Pointcloud Reintegrated Inference via Segmentation and Cross-attention for Manipulation

Daqi Huang, Zhehao Cai, Yuzhi Hao, Zechen Li, Chee-Meng Chew

机构 * National University of Singapore（新加坡国立大学） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.RO

4D mmWave Radar for Sensing Enhancement in Adverse Environments: Advances and Challenges

Xiangyuan Peng, Miao Tang, Huawei Sun, Kay Bierzynski, Lorenzo Servadei, Robert Wille

机构 * Technical University of Munich（慕尼黑技术大学） ； Infineon Technologies AG（英飞凌科技有限公司） ； China University of Geosciences（中国地质大学） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV

Comments 8 pages, accepted by ITSC2025

Label-Free Long-Horizon 3D UAV Trajectory Prediction via Motion-Aligned RGB and Event Cues

Hanfang Liang, Shenghai Yuan, Fen Liu, Yizhuo Yang, Bing Wang, Zhuyu Huang, Chenyang Shi, Jing Jin

机构 * Jianghan University（江汉大学） ； Nanyang Technological University（南洋理工大学） ； Beihang University (BUAA)（北京航空航天大学） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.RO

AnyI2V: Animating Any Conditional Image with Motion Control

Ziye Li, Hao Luo, Xincheng Shuai, Henghui Ding

机构 * Fudan University（复旦大学） ； DAMO Academy, Alibaba group（阿里达摩院） ； Hupan Lab（虎扑实验室） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV

Comments ICCV 2025, Project Page: https://henghuiding.com/AnyI2V/

MV2DFusion: Leveraging Modality-Specific Object Semantics for Multi-Modal 3D Detection

Zitian Wang, Zehao Huang, Yulu Gao, Naiyan Wang, Si Liu

机构 * Institute of Artificial Intelligence, Beihang University（北京航空航天大学人工智能学院） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV

SG-LDM: Semantic-Guided LiDAR Generation via Latent-Aligned Diffusion

Zhengkang Xiang, Zizhao Li, Amir Khodabandeh, Kourosh Khoshelham

机构 * The University of Melbourne（墨尔本大学） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV

Event-based Tiny Object Detection: A Benchmark Dataset and Baseline

Nuo Chen, Chao Xiao, Yimian Dai, Shiman He, Miao Li, Wei An

专题命中 点云 ：point cloud(abstract)；分类 cs.CV

Enhancing Spatial Reasoning in Multimodal Large Language Models through Reasoning-based Segmentation

Zhenhua Ning, Zhuotao Tian, Shaoshuai Shi, Guangming Lu, Daojing He, Wenjie Pei, Li Jiang

机构 * Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳）） ； Pengcheng Laboratory（鹏城实验室） ； The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）） ； Voyager Research, Didi Chuxing 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV

SSFold: Learning to Fold Arbitrary Crumpled Cloth Using Graph Dynamics from Human Demonstration

Changshi Zhou, Haichuan Xu, Jiarui Hu, Feng Luan, Zhipeng Wang, Yanchao Dong, Yanmin Zhou, Bin He

机构 * Shanghai Research Institute for Intelligent Autonomous Systems（上海智能自主系统研究院） ； National Key Laboratory of Autonomous Intelligent Unmanned Systems (Tongji University)（自主智能无人系统国家重点实验室（同济大学）） ； Frontiers Science Center for Intelligent Autonomous Systems（智能自主系统前沿科学中心） ； College of Electronics and Information Engineering, Tongji University（同济大学电子信息工程学院） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.RO

FlatFusion: Delving into Details of Sparse Transformer-based Camera-LiDAR Fusion for Autonomous Driving

Yutao Zhu, Xiaosong Jia, Xinyu Yang, Junchi Yan

机构 * School of Computer Science and School of Artificial Intelligence, Shanghai Jiao Tong University（计算机科学学院和人工智能学院，上海交通大学） ； Carnegie Mellon University（卡内基梅隆大学） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV

Comments Accepted by ICRA 2025

CA-I2P: Channel-Adaptive Registration Network with Global Optimal Selection

Zhixin Cheng, Jiacheng Deng, Xinjun Li, Xiaotian Yin, Bohao Liao, Baoqun Yin, Wenfei Yang, Tianzhu Zhang

机构 * School of Information Science and Technology, University of Science and Technology of China（信息科学与技术学院，中国科学技术大学） ； Institute of Advanced Technology, University of Science and Technology of China（先进技术研究院，中国科学技术大学） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV

Comments ICCV 2025 accepted

EFEAR-4D: Ego-Velocity Filtering for Efficient and Accurate 4D radar Odometry

Xiaoyi Wu, Yushuai Chen, Zhan Li, Ziyang Hong, Liang Hu

机构 * Department of Automation, School of Mechanical Engineering and Automation, Harbin Institute of Technology（自动化系，机械工程与自动化学院，哈尔滨工业大学） ； Research Institute of Intelligent Control and Systems, Harbin Institute of Technology（智能控制与系统研究院，哈尔滨工业大学） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.RO

SPARK: Graph-Based Online Semantic Integration System for Robot Task Planning

Mimo Shirasaka, Yuya Ikeda, Tatsuya Matsushima, Yutaka Matsuo, Yusuke Iwasawa

机构 * The University of Tokyo（东京大学） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.RO

BVMatch: Lidar-based Place Recognition Using Bird's-eye View Images

Lun Luo, Si-Yuan Cao, Bin Han, Hui-Liang Shen, Junwei Li

专题命中 点云 ：point cloud(abstract)；分类 cs.CV

Journal ref in IEEE Robotics and Automation Letters, vol. 6, no. 3, pp. 6076-6083, July 2021

Layered Motion Fusion: Lifting Motion Segmentation to 3D in Egocentric Videos

Vadim Tschernezki, Diane Larlus, Iro Laina, Andrea Vedaldi

机构 * Visual Geometry Group University of Oxford（视觉几何组牛津大学） ； NAVER LABS Europe（NAVER欧洲实验室） 纠错

专题命中 点云 ：3D vision(abstract)；分类 cs.CV

Comments Camera-ready for CVPR25

SDDiff: Boost Radar Perception via Spatial-Doppler Diffusion

Shengpeng Wang, Xin Luo, Yulong Xie, Wei Wang

机构 * Huazhong University of Science and Technology（华中科技大学） ； Wuhan University（武汉大学） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.RO

How Hard Is Snow? A Paired Domain Adaptation Dataset for Clear and Snowy Weather: CADC+

Mei Qi Tang, Sean Sedwards, Chengjie Huang, Krzysztof Czarnecki

机构 * University of Waterloo（滑铁卢大学） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV

Comments IEEE IV 2025

An Iterative Task-Driven Framework for Resilient LiDAR Place Recognition in Adverse Weather

Xiongwei Zhao, Xieyuanli Chen, Xu Zhu, Xingxiang Xie, Haojie Bai, Congcong Wen, Rundong Zhou, Qihao Sun

机构 * School of Electronic and Information Engineering, Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳）电子与信息工程学院） ； College of Intelligence Science and Technology, National University of Defense Technology（国防科技大学智能科学与技术学院） ； School of Information Communication Technology, Shenzhen Institute of Information Technology（深圳信息职业技术学院信息通信技术学院） ； Harvard AI and Robotics Lab, Harvard University（哈佛大学AI与机器人实验室） ； State Key Laboratory of Robotics and System, Harbin Institute of Technology（哈尔滨工业大学机器人系统国家重点实验室） ； School of Electronic and Communication Engineering, Shenzhen Polytechnic University（深圳职业技术大学电子与通信工程学院） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.RO

Comments Submitted to IEEE TVT

CooPre: Cooperative Pretraining for V2X Cooperative Perception

Seth Z. Zhao, Hao Xiang, Chenfeng Xu, Xin Xia, Bolei Zhou, Jiaqi Ma

机构 * University of California, Los Angeles（加州大学洛杉矶分校） ； University of California, Berkeley（加州大学伯克利分校） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV

Empirical Studies of Large Scale Environment Scanning by Consumer Electronics

Mengyuan Wang, Yang Liu, Haopeng Wang, Haiwei Dong, Abdulmotaleb El Saddik

机构 * University of Ottawa（Ottawa 大学） ； Huawei Canada（华为加拿大） 纠错

专题命中 点云 ：point cloud(abstract)；分类 cs.CV

Comments Accepted by IEEE Consumer Electronics Magazine