3D 视觉

Locating and Mitigating Gradient Conflicts in Point Cloud Domain Adaptation via Saliency Map Skewness

Jiaqi Tang, Yinsong Xu, Qingchao Chen

机构 * National Institute of Health Data Science, Peking University（北京大学国家健康数据科学研究院） ； Institute of Medical Technology, Peking University（北京大学医学技术研究院） ； State Key Laboratory of General Artificial Intelligence, Peking University（北京大学通用人工智能国家重点实验室） ； School of Artificial Intelligence, Beijing University of Posts and Telecommunications（北京邮电大学人工智能学院） 纠错

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

Efficient Implicit Neural Compression of Point Clouds via Learnable Activation in Latent Space

Yichi Zhang, Qianqian Yang

机构 * Zhejiang University（浙江大学） 纠错

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

Comments 8 pages

ROI-Guided Point Cloud Geometry Compression Towards Human and Machine Vision

Xie Liang, Gao Wei, Zhenghui Ming, Li Ge

机构 * Peking University Shenzhen Graduate School and Peng Cheng Laboratory（北京大学深圳研究生院和鹏城实验室） 纠错

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

Comments 10 pages, 5 figures

Journal ref ACM International Conference on Multimedia 2024

HFBRI-MAE: Handcrafted Feature Based Rotation-Invariant Masked Autoencoder for 3D Point Cloud Analysis

Xuanhua Yin, Dingxin Zhang, Jianhui Yu, Weidong Cai

机构 * School of Computer Science, The University of Sydney（计算机科学学院，悉尼大学） 纠错

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

Comments 12 pages, 9 figures, accepted by IJCNN 2025

RefComp: A Reference-guided Unified Framework for Unpaired Point Cloud Completion

Yixuan Yang, Jinyu Yang, Zixiang Zhao, Victor Sanchez, Feng Zheng

机构 * Southern University of Science and Technology（南方科技大学） ； University of Warwick（沃里克大学） ； Photogrammetry and Remote Sensing, ETH Zürich（摄影测量与遥感，苏黎世联邦理工学院） 纠错

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

ViG3D-UNet: Volumetric Vascular Connectivity-Aware Segmentation via 3D Vision Graph Representation

Bowen Liu, Chunlei Meng, Wei Lin, Hongda Zhang, Ziqing Zhou, Zhongxue Gan, Chun Ouyang

机构 * Academy for Engineering and Technology, Fudan University（复旦大学工程与技术学院） 纠错

专题命中 点云 ：3D vision(title,abstract)；分类 cs.CV

DG-MVP: 3D Domain Generalization via Multiple Views of Point Clouds for Classification

Huantao Ren, Minmin Yang, Senem Velipasalar

机构 * Syracuse University（雪城大学） 纠错

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

3D-PointZshotS: Geometry-Aware 3D Point Cloud Zero-Shot Semantic Segmentation Narrowing the Visual-Semantic Gap

Minmin Yang, Huantao Ren, Senem Velipasalar

机构 * Syracuse University（雪城大学） 纠错

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

Non-uniform Point Cloud Upsampling via Local Manifold Distribution

Yaohui Fang, Xingce Wang

机构 * Beijing Normal University（北京师范大学） 纠错

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

Intelligent driving vehicle front multi-target tracking and detection based on YOLOv5 and point cloud 3D projection

Dayong Liu, Qingrui Zhang, Zeyang Meng

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

Comments in Chinese language

PointDGMamba: Domain Generalization of Point Cloud Classification via Generalized State Space Model

Hao Yang, Qianyu Zhou, Haijia Sun, Xiangtai Li, Fengqi Liu, Xuequan Lu, Lizhuang Ma, Shuicheng Yan

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

Comments Published on Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) 2025;

Journal ref Proceedings of the AAAI Conference on Artificial Intelligence, 39(9), 9193-9201, 2025

Robust Unsupervised Domain Adaptation for 3D Point Cloud Segmentation Under Source Adversarial Attacks

Haosheng Li, Junjie Chen, Yuecong Xu, Kemi Ding

机构 * Southern University of Science and Technology（南方科技大学） ； National University of Singapore（新加坡国立大学） 纠错

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

ProtoGuard-guided PROPEL: Class-Aware Prototype Enhancement and Progressive Labeling for Incremental 3D Point Cloud Segmentation

Haosheng Li, Yuecong Xu, Junjie Chen, Kemi Ding

机构 * Southern University of Science and Technology（南方科技大学） ； National University of Singapore（新加坡国立大学） 纠错

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

CFSSeg: Closed-Form Solution for Class-Incremental Semantic Segmentation of 2D Images and 3D Point Clouds

Jiaxu Li, Rui Li, Jianyu Qi, Songning Lai, Linpu Lv, Kejia Fan, Jianheng Tang, Yutao Yue, Dongzhan Zhou, Yuanhuai Liu, Huiping Zhuang

机构 * Central South University（中南大学） ； The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） ； South China University of Technology（华南理工大学） ； Peking University（北京大学） ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； Zhengzhou University（郑州大学） 纠错

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

FACT: Multinomial Misalignment Classification for Point Cloud Registration

Ludvig Dillén, Per-Erik Forssén, Johan Edstedt

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

Comments Accepted at SCIA 2025 (the Scandinavian Conference on Image Analysis 2025)

POD: Predictive Object Detection with Single-Frame FMCW LiDAR Point Cloud

Yining Shi, Kun Jiang, Xin Zhao, Kangan Qian, Chuchu Xie, Tuopu Wen, Mengmeng Yang, Diange Yang

机构 * School of Vehicle and Mobility, Tsinghua University（清华大学车辆与学院） ； State Key Laboratory of Intelligent Green Vehicle and Mobility（智能绿色车辆与交通全国重点实验室） 纠错

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

TDFANet: Encoding Sequential 4D Radar Point Clouds Using Trajectory-Guided Deformable Feature Aggregation for Place Recognition

Shouyi Lu, Guirong Zhuo, Haitao Wang, Quan Zhou, Huanyu Zhou, Renbo Huang, Minqing Huang, Lianqing Zheng, Qiang Shu

机构 * School of Automotive Studies, Tongji University（同济大学汽车学院） ； Shanghai Geometrical Perception and Learning Co., Ltd.（上海几何感知与学习有限公司） ； Shanghai Tongyu Automotive Technology Co., Ltd.（上海同驭汽车科技有限公司） 纠错

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

Comments 8 pages, 4 figures. Accepted to ICRA 2025

Unsupervised 3D Point Cloud Completion via Multi-view Adversarial Learning

Lintai Wu, Xianjing Cheng, Yong Xu, Huanqiang Zeng, Junhui Hou

机构 * Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳）） ； City University of Hong Kong（香港城市大学） ； Huaqiao University（华侨大学） 纠错

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

Comments Accepted in IEEE TVCG

Robust Human Registration with Body Part Segmentation on Noisy Point Clouds

Kai Lascheit, Daniel Barath, Marc Pollefeys, Leonidas Guibas, Francis Engelmann

机构 * ETH Zurich（苏黎世联邦理工学院） ； Microsoft（微软公司） ； Stanford University（斯坦福大学） ； Google（谷歌公司） 纠错

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

PointCG: Self-supervised Point Cloud Learning via Joint Completion and Generation

Yun Liu, Peng Li, Xuefeng Yan, Liangliang Nan, Bing Wang, Honghua Chen, Lina Gong, Wei Zhao, Mingqiang Wei

机构 * School of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics（南京航空航天大学计算机科学与技术学院） ； Shenzhen Institute of Research, Nanjing University of Aeronautics and Astronautics（南京航空航天大学深圳研究院） ； Collaborative Innovation Center of Novel Software Technology and Industrialization（新型软件技术与产业化协同创新中心） ； Delft University of Technology（代尔夫特理工大学） ； The Hong Kong Polytechnic University（香港理工大学） 纠错

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

Multi-Head Adaptive Graph Convolution Network for Sparse Point Cloud-Based Human Activity Recognition

Vincent Gbouna Zakka, Luis J. Manso, Zhuangzhuang Dai

机构 * Aston University（阿斯顿大学） 纠错

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

CanonNet: Canonical Ordering and Curvature Learning for Point Cloud Analysis

Benjy Friedmann, Michael Werman

机构 * Hebrew University of Jerusalem（耶路撒冷希伯来大学） 纠错

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

Taylor Series-Inspired Local Structure Fitting Network for Few-shot Point Cloud Semantic Segmentation

Changshuo Wang, Shuting He, Xiang Fang, Meiqing Wu, Siew-Kei Lam, Prayag Tiwari

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

Journal ref AAAI 2025

Multimodal Point Cloud Semantic Segmentation With Virtual Point Enhancement

Zaipeng Duan, Xuzhong Hu, Pei An, Jie Ma

机构 * School of Artificial Intelligence and Automation, Huazhong University of Science and Technology (HUST)（华中科技大学人工智能与自动化学院） ； School of Electronic Information and Communications, Huazhong University of Science and Technology（华中科技大学电子信息与通信学院） 纠错

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

Hierarchical Attention Networks for Lossless Point Cloud Attribute Compression

Yueru Chen, Wei Zhang, Dingquan Li, Jing Wang, Ge Li

机构 * Pengcheng Laboratory（鹏城实验室） ； Peking University Shenzhen Graduate School（北京大学深圳研究生院） 纠错

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

Comments Accepted by DCC 2025

Introducing the Short-Time Fourier Kolmogorov Arnold Network: A Dynamic Graph CNN Approach for Tree Species Classification in 3D Point Clouds

Said Ohamouddou, Mohamed Ohamouddou, Hanaa El Afia, Abdellatif El Afia, Rafik Lasri, Raddouane Chiheb

机构 * ENSIAS, Mohammed V University（穆罕默德五世大学ENSIAS学院） ； FPL, Abdelmalek saadi University（阿卜杜勒-马利克·萨阿迪大学FPL学院） 纠错

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

Adaptive Multi-step Refinement Network for Robust Point Cloud Registration

Zhi Chen, Yufan Ren, Tong Zhang, Zheng Dang, Wenbing Tao, Sabine Süsstrunk, Mathieu Salzmann

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

Comments Accepted at TMLR'25

Joint Learning for Scattered Point Cloud Understanding with Hierarchical Self-Distillation

Kaiyue Zhou, Ming Dong, Peiyuan Zhi, Shengjin Wang

机构 * Tsinghua University（清华大学） ； Wayne State University（韦恩州立大学） 纠错

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

Comments Published version (early-view) without bios

Journal ref IEEE Sensors Journal ( Volume: 25, Issue: 3, 01 February 2025)

Spectral Informed Mamba for Robust Point Cloud Processing

Ali Bahri, Moslem Yazdanpanah, Mehrdad Noori, Sahar Dastani, Milad Cheraghalikhani, David Osowiechi, Gustavo Adolfo Vargas Hakim, Farzad Beizaee, Ismail Ben Ayed, Christian Desrosiers

机构 * ÉTS Montréal（蒙特利尔工程学院） ； International Laboratory on Learning Systems (ILLS)（国际学习系统实验室） 纠错

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

UniPCGC: Towards Practical Point Cloud Geometry Compression via an Efficient Unified Approach

Kangli Wang, Wei Gao

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

Comments Accepted to AAAI 2025