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 19082 信号源:cs.CV, cs.GR, cs.RO

1. 点云 7740 篇

2110.10494 2024-03-26 cs.CV cs.CG cs.GR 84%

Deep Point Cloud Normal Estimation via Triplet Learning

Weijia Wang, Xuequan Lu, Dasith de Silva Edirimuni, Xiao Liu, Antonio Robles-Kelly

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

Comments Accepted by ICME 2022. Supplementary material available at https://ieeexplore.ieee.org/document/9859844/media#media

详情

展开后加载摘要…

URL PDF HTML 收藏
2012.09242 2023-11-20 cs.CV cs.AI cs.LG cs.RO 84%

S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Clouds

Ran Cheng, Christopher Agia, Yuan Ren, Xinhai Li, Liu Bingbing

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

Comments 14 pages

Journal ref PMLR 155 (2021) 2148-2161

详情

展开后加载摘要…

URL PDF HTML 收藏
2106.15280 2021-06-30 cs.CV cs.GR 84%

Xihe: A 3D Vision-based Lighting Estimation Framework for Mobile Augmented Reality

Yiqin Zhao, Tian Guo

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2102.04136 2021-02-09 cs.CV cs.LG cs.RO 84%

Points2Vec: Unsupervised Object-level Feature Learning from Point Clouds

Joël Bachmann, Kenneth Blomqvist, Julian Förster, Roland Siegwart

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.17131 2026-06-18 cs.CV cs.AI cs.LG 版本更新 84%

A Survey on Deep Learning Architectures for Point Cloud Classification and Segmentation

针对点云分类和分割的深度学习架构系统性调研

Minhas Kamal, Hiranya Garbha Kumar, Balakrishnan Prabhakaran

机构 * State University of New York at Albany(纽约州立大学阿尔巴尼分校)

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

AI总结 本文系统性地探讨了点云分类和分割中的深度学习架构,分析了点云数据的结构特性,分类了不同架构的工作,并评估了其在主流基准上的性能,同时指出了开放挑战和未来方向。

Comments We reviewed a decade of advancements in point cloud processing: trace the evolution of the field from its foundational roots to the modern SOTA, analyze how diverse architectures overcome the inherent geometric challenges of 3D data, and map out critical research gaps alongside promising future directions. GitHub: https://github.com/MinhasKamal/DeepLearningForPointCloud

Journal ref ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.20740 2026-08-24 cs.CV 新提交 83%

VisTa3D: A Dataset and Benchmark for Thin Object Reconstruction from Vision, Tactile, and 3D Point Clouds

VisTa3D:用于从视觉、触觉和三维点云重建薄物体的数据集与基准

Shania Guo, Yeongsik Seo, Andrew Fu, Mei Hao, Iris Xia, Jiwon Jenny Lee, Xinyi Mary Xie, Hyoungseob Park, Aaron Dollar, Alex Wong

机构 * Yale University(耶鲁大学) Yale Vision Laboratory(耶鲁视觉实验室) GRAB Lab(GRAB实验室)

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

AI总结 VisTa3D是首个含视觉、触觉等数据的薄物体重建数据集,作者在其上基准测试现有模型发现其保真度低,还提出视觉-深度-触觉基线模型以探究触觉数据对薄物体重建的辅助作用。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.11273 2026-08-13 eess.IV cs.CV cs.MM 新提交 83%

Geometry-Based Compression of Plenoptic Point Clouds

基于几何的全光点云压缩

Davi R. Freitas, Gustavo L. Sandri, Ricardo L. de Queiroz

机构 * Inria - Rennes Bretagne-Atlantique(法国国家信息与自动化研究所雷恩布列塔尼-大西洋分所)

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

AI总结 提出一种整合进MPEG G-PCC标准的PPC属性压缩方法,经不同分辨率PPC测试,性能优于现有同类方案,有望成为新最优方案。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.01759 2026-07-28 cs.CV 83%

PointCSP: Cross-Sample Semantic Propagation and Stability Preservation in Self-Supervised Point Cloud Learning

PointCSP:自监督点云学习中的跨样本语义传播与稳定性保持

Xinxing Yu, Ajian Liu, Sunyuan Qiang, Hui Ma, Liying Yang, Yuzhong Wang, Zhi Rao, Yanyan Liang

机构 * Faculty of Innovation Engineering, Macau University of Science and Technology(澳门科技大学创新工程学院) Southwest Institute of Technical Physics(西南技术物理研究所) The Institute of Automation of the Chinese Academy of Sciences(中国科学院自动化研究所) School of Computing and Information Technology, Great Bay University(湾区大学计算与信息技术学院)

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

AI总结 研究点云自监督学习中跨场景语义一致性问题,提出基于跨样本语义传播的PC-SSL框架及非对称语义保持蒸馏,在状态空间显式建模样本动态依赖,实现跨样本语义对齐与稳定转移,实验证明性能优于现有方法。

Comments conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.18472 2026-06-18 cs.CV 新提交 83%

Domain Generalizable Adaptation of 3D Vision-Language Models via Regularized Fine-Tuning

通过正则化微调实现可域泛化的3D视觉-语言模型适应

Sneha Paul, Zachary Patterson, Nizar Bouguila

机构 * Concordia University(康考迪亚大学)

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

AI总结 提出ReFine3D框架,通过选择性层调优、多视图一致性、同义词提示及点渲染视觉监督等正则化策略,提升3D大语言模型在域泛化中的性能。

Comments Accepted at Transactions on Machine Learning Research (TMLR)

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.04291 2026-06-04 cs.CV 83%

A Cookbook of 3D Vision: Data, Learning Paradigms, and Application

3D视觉食谱:数据、学习范式与应用

Hongyang Du, Zongxia Li, Dawei Liu, Runhao Li, Haoyuan Song, Qingyu Zhang, Yubo Wang, Jingcheng Ni, Shihang Gui, Congchao Dong, Tao Hu

机构 * Brown University(布朗大学) University of Maryland, College Park(马里兰大学学院公园分校) University of Pennsylvania(宾夕法尼亚大学) University of Southern California(南加州大学) New York University(纽约大学) The University of Sydney(悉尼大学) Stability AI

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

AI总结 本文提出一种以数据为中心的3D视觉分类法,通过分析点云、网格、体素和3D高斯等几何表示及其获取流程,以及数据集设计、基准构建和监督机制,统一了表示、学习范式与下游任务(重建、生成、视频建模)之间的关系。

Comments Accepted to the CVPR 2026 OpenSUN3D Workshop. Official version available at CVF Open Access. https://openaccess.thecvf.com/content/CVPR2026W/OpenSUN3D/html/Du_A_Cookbook_of_3D_Vision_Data_Learning_Paradigms_and_Application_CVPRW_2026_paper.html

Journal ref Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.25859 2026-06-03 cs.CV cs.SY eess.SY 83%

LiDAR Point Cloud Colourisation Using Multi-Camera Fusion and Low-Light Image Enhancement

使用多相机融合和低光图像增强的LiDAR点云着色

Pasindu Ranasinghe, Dibyayan Patra, Bikram Banerjee, Simit Raval

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

AI总结 提出一种硬件无关的方法,通过多相机融合和低光增强模块,实现机械LiDAR点云的360度着色,在低光照条件下仍能恢复场景细节。

Journal ref Sensors 25(21), 6582 (2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.05897 2026-05-08 cs.RO 83%

Generating Roadside LiDAR Datasets from Vehicle-Side Datasets via Novel View Synthesis

通过新颖视角合成从车辆侧数据生成道路侧LiDAR数据集

Yuhan Xia, Runxin Zhao, Hanyang Zhuang, Chunxiang Wang, Ming Yang

机构 * School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai 200240, China(自动化与智能感知学院,上海交通大学,上海200240,中国) Key Laboratory of System Control and Information Processing, Ministry of Education of China, Shanghai 200240, China(系统控制与信息处理重点实验室,中华人民共和国教育部,上海200240,中国) Global College, Shanghai Jiao Tong University, Shanghai 200240, China(全球学院,上海交通大学,上海200240,中国)

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

AI总结 本文提出VRS框架,通过LiDAR新颖视角合成从车辆侧数据生成标注道路侧LiDAR数据集,缓解车辆到道路域差距,提升道路侧感知模型的泛化能力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.15703 2026-04-20 cs.CV 83%

P3T: Prototypical Point-level Prompt Tuning with Enhanced Generalization for 3D Vision-Language Models

P3T: 用于3D视觉-语言模型的增强泛化原型点级提示微调

Geunyoung Jung, Soohong Kim, Kyungwoo Song, Jiyoung Jung

机构 * Department of Artificial Intelligence, University of Seoul(首尔大学人工智能系) Department of Applied Statistics, Yonsei University(延世大学应用统计系)

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

AI总结 本文提出P3T,一种针对3D视觉-语言模型的高效提示微调方法,通过点级提示器和文本提示器提升模型泛化能力,并引入原型损失减少类别内方差,实验表明其在分类和少样本学习中表现优异。

Comments Accepted by ICRA 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.22070 2026-03-26 cs.CV 83%

Adapting Point Cloud Analysis via Multimodal Bayesian Distribution Learning

通过多模态贝叶斯分布学习适应点云分析

Xingyu Zhu, Liang Yi, Shuo Wang, Wenbo Zhu, Yonglinag Wu, Beier Zhu, Hanwang Zhang

机构 * MoE Key Lab of BIPC, University of Science and Technology of China(脑信息处理实验室,中国科学技术大学) Opus AI Research(Opus AI研究院) Southeast University(东南大学) Nanyang Technological University(南洋理工大学)

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

AI总结 本文提出BayesMM框架,通过多模态贝叶斯分布学习实现测试时点云分析的持续适应,利用文本先验和流式视觉特征的高斯分布融合,提升在分布偏移下的鲁棒性。

Comments CVPR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.16945 2026-03-19 cs.CV cs.AI 83%

Joint Optimization of Storage and Loading for High-Performance 3D Point Cloud Data Processing

高绩效3D点云数据处理中存储与加载的联合优化

Ke Wang, Yanfei Cao, Xiangzhi Tao, Naijie Gu, Jun Yu, Zhengdong Wang, Shouyang Dong, Fan Yu, Cong Wang, Yang Luo

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

AI总结 本文提出.PcRecord格式和高效数据处理流水线,通过多阶段并行架构优化计算资源,提升大规模点云数据处理效率,实验显示在多个数据集上性能提升显著。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.14309 2026-03-17 cs.CV 83%

In-Field 3D Wheat Head Instance Segmentation From TLS Point Clouds Using Deep Learning Without Manual Labels

基于TLS点云的田间小麦头实例分割:无需手动标注的深度学习方法

Tomislav Medic, Liangliang Nan

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

AI总结 本文提出一种无需手动标注的深度学习方法,直接从TLS点云中实现田间小麦头实例分割,通过两阶段流程提升分割效果,优于现有基于多视角RGB图像和3D高斯点划法的解决方案。

Comments to be published in ISPRS Annals of Photogrammetry and Remote Sensing at XXV ISPRS Congress, Toronto, Canada, July 2026, 8 pages, 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.12721 2026-03-16 cs.CV cs.AI 83%

CMHANet: A Cross-Modal Hybrid Attention Network for Point Cloud Registration

CMHANet:一种用于点云配准的跨模态混合注意力网络

Dongxu Zhang, Yingsen Wang, Yiding Sun, Haoran Xu, Peilin Fan, Jihua Zhu

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

AI总结 本文提出CMHANet,通过融合2D图像与3D点云信息,提升配准鲁棒性,并引入对比学习优化函数,实验表明在3DMatch和3DLoMatch数据集上效果优于现有方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.12719 2026-03-16 cs.CV cs.AI 83%

IGASA: Integrated Geometry-Aware and Skip-Attention Modules for Enhanced Point Cloud Registration

IGASA: 集成几何感知和跳过注意力模块的增强点云配准

Dongxu Zhang, Jihua Zhu, Shiqi Li, Wenbiao Yan, Haoran Xu, Peilin Fan, Huimin Lu

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

AI总结 本文提出IGASA框架,通过层次金字塔架构和HCLA、IGAR模块提升点云配准的鲁棒性和精度,实验表明其在多个基准数据集上优于现有方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.00412 2026-03-03 cs.CV 83%

PointAlign: Feature-Level Alignment Regularization for 3D Vision-Language Models

PointAlign:用于3D视觉-语言模型的特征级对齐正则化

Yuanhao Su, Shaofeng Zhang, Xiaosong Jia, Qi Fan

机构 * University of Science and Technology of China(中国科学技术大学) Fuzhou University(福州大学) Fudan University(复旦大学) Nanjing University(南京大学)

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

AI总结 PointAlign通过特征级对齐正则化提升3D视觉-语言模型的几何信息保留与任务性能

Comments CVPR 2026 Accepted

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.10492 2026-03-03 cs.CV eess.IV 83%

MFP3D: Monocular Food Portion Estimation Leveraging 3D Point Clouds

MFP3D:利用3D点云的单目食物分量估计

Jinge Ma, Xiaoyan Zhang, Gautham Vinod, Siddeshwar Raghavan, Jiangpeng He, Fengqing Zhu

机构 * Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, USA(电气与计算机工程学院,普渡大学,西拉法叶,美国) College of Artificial Intelligence, Anhui University, Hefei, China(人工智能学院,安徽大学,合肥,中国)

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

AI总结 MFP3D通过单目图像和3D点云技术实现准确的食物分量估计,提升饮食监控的精度。

Comments 9th International Workshop on Multimedia Assisted Dietary Management, in conjunction with the 27th International Conference on Pattern Recognition (ICPR2024)

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.08414 2026-02-09 cs.CV 83%

SPARK: Scalable Real-Time Point Cloud Aggregation with Multi-View Self-Calibration

SPARK:可扩展的实时点云聚合与多视角自校准

Chentian Sun

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

AI总结 SPARK通过自校准实时多摄像机点云重建框架,实现稳定且高效的点云融合与外参估计,适用于大规模3D重建场景。

Comments 10 pages, 1 figure, submitted to IEEE Transactions on Image Processing (TIP). Version 3: Minor revision; several experimental results have been removed and supplemented after further verification

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.17229 2026-01-29 cs.CV 83%

Range Image-Based Implicit Neural Compression for LiDAR Point Clouds

基于范围图像的隐式神经压缩用于LiDAR点云

Akihiro Kuwabara, Sorachi Kato, Toshiaki Koike-Akino, Takuya Fujihashi

机构 * Graduate School of Information Science and Technology(信息科学与技术研究生学校) The University of Osaka(大阪大学) Mitsubishi Electric Research Laboratories (MERL)(三菱电机研究实验室(MERL))

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

AI总结 本文提出基于隐式神经表示的范围图像压缩方法,通过分割深度和掩码图像并采用模型剪枝和量化技术,实现对LiDAR点云的高效压缩。

Comments Accepted for publication in IEEE Access

Journal ref IEEE Access, vol. 14, pp. 10262-10275, 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.06839 2026-01-13 cs.CV 83%

PRISM: Color-Stratified Point Cloud Sampling

PRISM:基于颜色分层的点云采样

Hansol Lim, Minhyeok Im, Jongseong Brad Choi

机构 * Department of Mechanical Engineering, State University of New York, Korea, Incheon, South Korea(纽约州立大学机械工程系) Department of Mechanical Engineering, State University of New York, Stony Brook, NY, United States(纽约州立大学石溪分校机械工程系) Department of Computer Science, State University of New York, Korea, Incheon, South Korea(纽约州立大学计算机科学系) Department of Computer Science, State University of New York, Stony Brook, NY, United States(纽约州立大学石溪分校计算机科学系)

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

AI总结 PRISM通过颜色引导分层采样方法,在RGB-LiDAR点云中保留高颜色变化区域,减少视觉同质表面,提升3D重建的点云质量。

Comments This work has been submitted to the 2026 International Conference on Pattern Recognition (ICPR) for possible publication

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.10386 2026-01-06 cs.CV 83%

Adaptive Dual-Weighted Gravitational Point Cloud Denoising Method

自适应双权重引力点云去噪方法

Ge Zhang, Chunyang Wang, Bin Liu, Guan Xi

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

AI总结 本文提出一种自适应双权重引力点云去噪方法,通过八叉树空间划分、自适应体素统计和引力评分函数,提升去噪精度、边缘保持和实时性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.11210 2025-12-09 cs.CV 83%

STONE: Pioneering the One-to-N Universal Backdoor Threat in 3D Point Cloud

STONE:开创性地探索3D点云中的一对多通用后门威胁

Dongmei Shan, Wei Lian, Chongxia Wang

机构 * Changzhi University(长治大学)

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

AI总结 STONE首次提出3D点云中一对多通用后门威胁,通过可配置球形触发器设计实现高攻击成功率,为多目标后门威胁提供理论与实证基础。

Comments 15 pages, 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.07076 2025-12-04 cs.CV cs.AI 83%

Representation Learning of Point Cloud Upsampling in Global and Local Inputs

全局和局部输入下的点云上采样表示学习

Tongxu Zhang, Bei Wang

机构 * East China University of Science and Technology(东华大学) The Hong Kong Polytechnic University(香港理工大学)

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

AI总结 本研究提出ReLPU框架,通过结合全局和局部特征学习提升点云上采样的性能和可解释性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2407.04476 2025-12-04 cs.CV cs.LG 83%

Rethinking Data Input for Point Cloud Upsampling

重新思考点云上采样中的数据输入

Tongxu Zhang

机构 * The Hong Kong Polytechnic University(香港理工大学)

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

AI总结 本文提出使用整体模型输入进行点云上采样,通过实验发现基于补丁的输入性能更优,并分析了影响上采样结果的关键因素。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.22908 2025-12-01 cs.CV 83%

ViGG: Robust RGB-D Point Cloud Registration using Visual-Geometric Mutual Guidance

ViGG: 基于视觉-几何互指导的鲁棒RGB-D点云配准

Congjia Chen, Shen Yan, Yufu Qu

机构 * Beihang University(北航大学) China Agricultural University(中国农业大学)

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

AI总结 ViGG通过视觉-几何互指导策略提升RGB-D点云配准的鲁棒性,优于现有方法。

Comments Accepted by WACV 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.21574 2025-11-27 cs.CV cs.AI 83%

Multimodal Robust Prompt Distillation for 3D Point Cloud Models

多模态鲁棒提示蒸馏用于3D点云模型

Xiang Gu, Liming Lu, Xu Zheng, Anan Du, Yongbin Zhou, Shuchao Pang

机构 * Xiang Gu 1 , Liming Lu 1 1 1 footnotemark: 1 , Xu Zheng 2,3 , Anan Du 4 , Yongbin Zhou 1 , Shuchao Pang 1 2 2 footnotemark: 2(某大学)

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

AI总结 多模态鲁棒提示蒸馏通过多模态知识蒸馏提升3D点云模型的鲁棒性,有效防御多种对抗攻击。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.15311 2025-11-24 cs.CV 83%

Adapt-As-You-Walk Through the Clouds: Training-Free Online Test-Time Adaptation of 3D Vision-Language Foundation Models

在云中适应:无需训练的在线测试时适应3D视觉-语言基础模型

Mehran Tamjidi, Hamidreza Dastmalchi, Mohammadreza Alimoradijazi, Ali Cheraghian, Aijun An, Morteza Saberi

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

AI总结 Uni-Adapter通过动态原型学习和熵加权聚合,在无需重新训练的情况下提升3D VLFMs在不同基准测试中的性能。

Comments Accepted by AAAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏