arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

视觉与机器人

3D 视觉

三维重建、NeRF、Gaussian Splatting、点云和空间智能。

共收录 7719 信号源:cs.CV, cs.GR, cs.RO

1. 点云 7719 篇

2509.16098 2025-12-01 cs.CV 57%

SegDINO3D: 3D Instance Segmentation Empowered by Both Image-Level and Object-Level 2D Features

SegDINO3D: 由图像级和物体级2D特征共同赋能的3D实例分割

Jinyuan Qu, Hongyang Li, Xingyu Chen, Shilong Liu, Yukai Shi, Tianhe Ren, Ruitao Jing, Lei Zhang

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

AI总结 SegDINO3D通过结合图像级和物体级2D特征,提升3D实例分割性能,在ScanNet200数据集上取得显著优势。

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.06597 2025-12-01 cs.RO 57%

LiHRA: A LiDAR-Based HRI Dataset for Automated Risk Monitoring Methods

LiHRA:基于LiDAR的人机交互风险监测数据集

Frederik Plahl, Georgios Katranis, Ilshat Mamaev, Andrey Morozov

机构 * Proximity Robotics & Automation GmbH(近距机器人与自动化有限公司) Institute of Industrial Automation and Software Engineering, University of Stuttgart(工业自动化与软件工程学院,斯图加特大学)

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

AI总结 LiHRA数据集通过多模态数据支持人机交互风险监测方法的开发,提供高分辨率LiDAR数据和真实碰撞事件,用于训练和评估RM算法。

Comments Preprint of final paper that will appear in the Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.21422 2025-11-27 cs.CV 57%

E-M3RF: An Equivariant Multimodal 3D Re-assembly Framework

E-M3RF:一个等价多模态3D重装配框架

Adeela Islam, Stefano Fiorini, Manuel Lecha, Theodore Tsesmelis, Stuart James, Pietro Morerio, Alessio Del Bue

机构 * Fondazione Istituto Italiano di Tecnologia(意大利技术研究院) University of Genova(热那亚大学) Durham University(杜伦大学)

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

AI总结 E-M3RF通过多模态特征融合和SE(3)流匹配,有效提升3D碎片重装配的精度与鲁棒性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.16833 2025-11-27 cs.CV 57%

Open Vocabulary Monocular 3D Object Detection

开放词汇单目3D物体检测

Jin Yao, Hao Gu, Xuweiyi Chen, Jiayun Wang, Zezhou Cheng

机构 * University of Virginia(弗吉尼亚大学) California Institute of Technology(加州理工学院)

专题命中 点云 :3D vision(abstract);分类 cs.CV

AI总结 本文提出了一种开放词汇单目3D检测方法,通过整合预训练的2D和3D视觉模型,解决3D标注稀缺和语义歧义问题,实现对新类别的零样本检测和已有类别的域内检测。

Comments 3DV 2026, Project page: https://cvlab.cs.virginia.edu/ovmono3d

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.19760 2025-11-26 cs.CV 57%

A Storage-Efficient Feature for 3D Concrete Defect Segmentation to Replace Normal Vector

一种用于3D混凝土缺陷分割的存储高效特征以替代法向量

Linxin Hua, Jianghua Deng, Ye Lu

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

AI总结 本研究提出相对角度作为3D混凝土缺陷分割的存储高效特征,替代传统法向量,实现27.6%的存储减少和83%的输入通道压缩,同时保持模型性能。

Comments 25 pages, 7 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.11895 2025-11-26 cs.CV 57%

Adversarial Robustness for Unified Multi-Modal Encoders via Efficient Calibration

通过高效校准实现统一多模态编码器的对抗鲁棒性

Chih-Ting Liao, Zhangquan Chen, Chunlei Meng, Tzu-Yu Huang, Xin Cao, Xu Zheng

机构 * UNSW Sydney(新南威尔士大学悉尼分校) Tsinghua University(清华大学) Fudan University(复旦大学) UTS(澳大利亚UTS大学) HKUST(GZ)(香港理工大学(广州))

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

AI总结 本研究提出高效对抗校准框架,提升统一多模态编码器的对抗鲁棒性,同时保持清洁性能,提升47.3%的鲁棒性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.03277 2025-11-25 cs.CV 57%

PointAD+: Learning Hierarchical Representations for Zero-shot 3D Anomaly Detection

PointAD+: 学习层次化表示用于零样本3D异常检测

Qihang Zhou, Shibo He, Jiangtao Yan, Wenchao Meng, Jiming Chen

机构 * State Key Laboratory of Industrial Control Technology(工业控制技术国家重点实验室) Zhejiang University(浙江大学)

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

AI总结 PointAD+通过层次化表示学习,结合隐式和显式异常语义,提升零样本3D异常检测性能。

Comments Submitted to TPAMI

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.23206 2025-11-25 cs.CV 57%

HyperPointFormer: Multimodal Fusion in 3D Space with Dual-Branch Cross-Attention Transformers

HyperPointFormer: 在三维空间中通过双分支交叉注意力变换器实现多模态融合

Aldino Rizaldy, Richard Gloaguen, Fabian Ewald Fassnacht, Pedram Ghamisi

机构 * Helmholtz-Zentrum Dresden-Rossendorf (HZDR)(德累斯顿-罗斯托克亥姆霍尔茨研究中心) Freie Universität Berlin(柏林自由大学)

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

AI总结 HyperPointFormer通过双分支交叉注意力Transformer在三维空间中融合多模态数据,提升城市场景土地利用分类的精度与灵活性。

Journal ref IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 18, pp. 21254-21274, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.11461 2025-11-25 cs.RO 57%

Doppler Correspondence: Non-Iterative Scan Matching With Doppler Velocity-Based Correspondence

多普勒对应:基于多普勒速度的非迭代扫描匹配

Jiwoo Kim, Geunsik Bae, Changseung Kim, Jinwoo Lee, Woojae Shin, Hyondong Oh

机构 * Department of Mechanical Engineering, Ulsan National Institute of Science and Technology, Republic of Korea(韩国乌山国立科学与技术研究院机械工程系) Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, Republic of Korea(韩国先进科学技术研究院机械工程系)

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

AI总结 本文提出基于多普勒速度的非迭代扫描匹配方法,通过利用4D激光雷达和雷达的多普勒信息,提高在恶劣环境下的里程计鲁棒性和计算效率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.18424 2025-11-25 cs.CV 57%

CrossJEPA: Cross-Modal Joint-Embedding Predictive Architecture for Efficient 3D Representation Learning from 2D Images

跨模态联合嵌入预测架构CrossJEPA:用于从2D图像高效学习3D表示的架构

Avishka Perera, Kumal Hewagamage, Saeedha Nazar, Kavishka Abeywardana, Hasitha Gallella, Ranga Rodrigo, Mohamed Afham

机构 * University of Moratuwa(摩图瓦大学) Technische Universität Darmstadt(达姆施塔特技术大学)

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

AI总结 CrossJEPA通过跨模态联合嵌入预测架构,利用图像基础模型知识,实现高效3D表示学习,达到SOTA性能,且训练高效、内存占用低。

Comments 24 pages, 10 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.17455 2025-11-24 cs.CV 57%

Improving Multimodal Distillation for 3D Semantic Segmentation under Domain Shift

改进多模态蒸馏以应对激光雷达语义分割中的域移位

Björn Michele, Alexandre Boulch, Gilles Puy, Tuan-Hung Vu, Renaud Marlet, Nicolas Courty

机构 * CNRS, IRISA, Univ. Bretagne Sud(CNRS、IRISA、布列塔尼大学) LIGM, Ecole des Ponts, Univ Gustave Eiffel, CNRS(LIGM、巴黎理工学院、古斯塔夫·埃菲尔大学、CNRS)

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

AI总结 本研究提出改进多模态蒸馏方法,通过冻结预训练主干网络并训练MLP头,提升激光雷达语义分割在域移位下的性能。

Comments Accepted at BMVC 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.17269 2025-11-24 cs.CV cs.AI 57%

Range-Edit: Semantic Mask Guided Outdoor LiDAR Scene Editing

Range-Edit: 基于语义掩码的户外激光雷达场景编辑

Suchetan G. Uppur, Hemant Kumar, Vaibhav Kumar

机构 * GeoAI4Cities Lab(GeoAI4Cities实验室) IISER Bhopal(印度比哈尔理工学院)

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

AI总结 Range-Edit通过语义掩码指导生成高质量的激光雷达点云,提升自动驾驶系统的鲁棒性与泛化能力。

Comments 8 pages, 9 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.16650 2025-11-21 cs.CV 57%

Late-decoupled 3D Hierarchical Semantic Segmentation with Semantic Prototype Discrimination based Bi-branch Supervision

迟解耦的3D层次语义分割与基于语义原型判别的双分支监督

Shuyu Cao, Chongshou Li, Jie Xu, Tianrui Li, Na Zhao

机构 * School of Computing and AI, Southwest Jiaotong University, Chengdu, China(计算机与人工智能学院,西南交通大学,成都,中国) Singapore University of Technology and Design, Singapore(新加坡科技设计大学,新加坡)

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

AI总结 本文提出了一种迟解耦的3D层次语义分割框架,结合基于语义原型的双分支监督机制,以解决多层次冲突和类别不平衡问题,实现更准确的3D场景分割。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.16140 2025-11-21 cs.CV 57%

Real-Time 3D Object Detection with Inference-Aligned Learning

基于推理对齐学习的实时3D物体检测

Chenyu Zhao, Xianwei Zheng, Zimin Xia, Linwei Yue, Nan Xue

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

AI总结 SR3D通过空间优先级最优传输分配和排名意识自适应自蒸馏方案,提升实时3D物体检测的准确性和效率

Comments Accepted by AAAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.16049 2025-11-21 cs.CV 57%

LiSTAR: Ray-Centric World Models for 4D LiDAR Sequences in Autonomous Driving

LiSTAR: 基于4D激光雷达序列的射线中心世界模型用于自动驾驶

Pei Liu, Songtao Wang, Lang Zhang, Xingyue Peng, Yuandong Lyu, Jiaxin Deng, Songxin Lu, Weiliang Ma, Xueyang Zhang, Yifei Zhan, XianPeng Lang, Jun Ma

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

AI总结 LiSTAR通过射线中心变换器和混合柱形球形表示,实现高保真4D激光雷达数据生成,提升自动驾驶模拟的可控性和真实性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.15153 2025-11-20 cs.CV 57%

SceneEdited: A City-Scale Benchmark for 3D HD Map Updating via Image-Guided Change Detection

Chun-Jung Lin, Tat-Jun Chin, Sourav Garg, Feras Dayoub

机构 * Australian Institute for Machine Learning (AIML), University of Adelaide, Australia(澳大利亚机器学习研究所(AIML)、阿德莱德大学)

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

Comments accepted by WACV 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.15077 2025-11-20 cs.CV 57%

MambaTrack3D: A State Space Model Framework for LiDAR-Based Object Tracking under High Temporal Variation

Shengjing Tian, Yinan Han, Xiantong Zhao, Xuehu Liu, Qi Lang

机构 * School of Economics and Management, China University of Mining and Technology(经济管理学院,中国矿业大学)

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

Comments This work has been submitted to a journal for possible publication

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.13647 2025-11-18 cs.CV 57%

Part-X-MLLM: Part-aware 3D Multimodal Large Language Model

Chunshi Wang, Junliang Ye, Yunhan Yang, Yang Li, Zizhuo Lin, Jun Zhu, Zhuo Chen, Yawei Luo, Chunchao Guo

机构 * Zhejiang University(浙江大学) Tencent Hunyuan(腾讯文言) Tsinghua University(清华大学) The University of Hong Kong(香港大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.13309 2025-11-18 cs.CV 57%

DriveLiDAR4D: Sequential and Controllable LiDAR Scene Generation for Autonomous Driving

Kaiwen Cai, Xinze Liu, Xia Zhou, Hengtong Hu, Jie Xiang, Luyao Zhang, Xueyang Zhang, Kun Zhan, Yifei Zhan, Xianpeng Lang

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

Comments AAAI2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.12757 2025-11-18 cs.CV cs.AI 57%

Which Way from B to A: The role of embedding geometry in image interpolation for Stable Diffusion

Nicholas Karris, Luke Durell, Javier Flores, Tegan Emerson

机构 * Department of Mathematics University of California, San Diego(数学系 加州大学圣地亚哥分校) National Security Directorate Pacific Northwest National Laboratory(国家安全局 西部国家实验室) Earth and Biological Sciences Directorate Pacific Northwest National Laboratory(地球与生命科学局 西部国家实验室)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.12117 2025-11-18 cs.CV 57%

RadarMP: Motion Perception for 4D mmWave Radar in Autonomous Driving

Ruiqi Cheng, Huijun Di, Jian Li, Feng Liu, Wei Liang

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

Comments 12 pages, 6 figures. Accepted by AAAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.11735 2025-11-18 cs.CV eess.IV 57%

Toward bilipshiz geometric models

Yonatan Sverdlov, Eitan Rosen, Nadav Dym

机构 * Faculty of Mathematics(数学系) Technion – Israel Institute of Technology(技术ion-以色列理工学院)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.11702 2025-11-18 cs.CV cs.AI eess.IV 57%

Task-Aware 3D Affordance Segmentation via 2D Guidance and Geometric Refinement

Lian He, Meng Liu, Qilang Ye, Yu Zhou, Xiang Deng, Gangyi Ding

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.13203 2025-11-18 cs.CV 57%

Is clustering enough for LiDAR instance segmentation? A state-of-the-art training-free baseline

Corentin Sautier, Gilles Puy, Alexandre Boulch, Renaud Marlet, Vincent Lepetit

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

Comments Accepted at 3DV 2026 Alpine ranks first in the leaderboard of SemanticKITTI's panoptic segmentation

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.11168 2025-11-17 cs.CV 57%

CATS-V2V: A Real-World Vehicle-to-Vehicle Cooperative Perception Dataset with Complex Adverse Traffic Scenarios

Hangyu Li, Bofeng Cao, Zhaohui Liang, Wuzhen Li, Juyoung Oh, Yuxuan Chen, Shixiao Liang, Hang Zhou, Chengyuan Ma, Jiaxi Liu, Zheng Li, Peng Zhang, KeKe Long, Maolin Liu, Jackson Jiang, Chunlei Yu, Shengxiang Liu, Hongkai Yu, Xiaopeng Li

机构 * University of Wisconsin-Madison(威斯康星大学麦迪逊分校) wuwen-ai Cleveland State University(克利夫兰州立大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.07375 2025-11-17 cs.CV 57%

Novel Diffusion Models for Multimodal 3D Hand Trajectory Prediction

Junyi Ma, Wentao Bao, Jingyi Xu, Guanzhong Sun, Xieyuanli Chen, Hesheng Wang

机构 * IRMV Lab, the Department of Automation, Shanghai Jiao Tong University(IRMV实验室,自动化系,上海交通大学) Meta Reality Labs(Meta现实实验室) the Department of Electronic Engineering, Shanghai Jiao Tong University(电子工程系,上海交通大学) the School of Information and Control Engineering, China University of Mining and Technology(信息与控制工程学院,中国矿业大学) the College of Intelligence Science and Technology, National University of Defense Technology(智能科学与技术学院,国防科技大学)

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

Comments Accepted to IROS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.10017 2025-11-14 cs.CV 57%

AffordBot: 3D Fine-grained Embodied Reasoning via Multimodal Large Language Models

Xinyi Wang, Xun Yang, Yanlong Xu, Yuchen Wu, Zhen Li, Na Zhao

机构 * University of Science and Technology of China(科学技术大学) Singapore University of Technology and Design(新加坡科技设计大学) Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳))

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

Comments NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.09883 2025-11-14 cs.CV 57%

HCC-3D: Hierarchical Compensatory Compression for 98% 3D Token Reduction in Vision-Language Models

Liheng Zhang, Jin Wang, Hui Li, Bingfeng Zhang, Weifeng Liu

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.09866 2025-11-14 cs.CV 57%

IPCD: Intrinsic Point-Cloud Decomposition

Shogo Sato, Takuhiro Kaneko, Shoichiro Takeda, Tomoyasu Shimada, Kazuhiko Murasaki, Taiga Yoshida, Ryuichi Tanida, Akisato Kimura

机构 * NTT Corporation(日本通信用电讯技术研究所)

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

Comments Accepted in WACV2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.08833 2025-11-13 cs.CV 57%

Enhancing Rotation-Invariant 3D Learning with Global Pose Awareness and Attention Mechanisms

Jiaxun Guo, Manar Amayri, Nizar Bouguila, Xin Liu, Wentao Fan

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

Comments 14 pages, 6 gigures,AAAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏