arXivDaily arXiv每日学术速递 周一至周五更新

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 18954 信号源:cs.CV, cs.GR, cs.RO

1. 三维重建 4384 篇

2603.21436 2026-03-24 cs.CV 83%

PAS3R: Pose-Adaptive Streaming 3D Reconstruction for Long Video Sequences

PAS3R:面向长视频序列的姿态自适应流式3D重建

Lanbo Xu, Liang Guo, Caigui Jiang, Cheng Wang

机构 * State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, China(人机混合增强智能国家重点实验室,人工智能与机器人研究院,西安交通大学,中国) University of East Anglia, Norwich, NR47TJ, United Kingdom(东安格利亚大学,诺里奇,英国)

专题命中 三维重建 :3D reconstruction(title,abstract);point cloud(abstract);分类 cs.CV

AI总结 PAS3R通过动态调节状态更新机制,解决流式3D重建中视角变化与结构稳定性矛盾,提升长视频序列的轨迹精度和点云重建质量。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.19926 2026-03-23 cs.CV 83%

SegVGGT: Joint 3D Reconstruction and Instance Segmentation from Multi-View Images

SegVGGT:从多视角图像联合进行3D重建和实例分割

Jinyuan Qu, Hongyang Li, Lei Zhang

机构 * Tsinghua University(清华大学) South China University of Technology(华南理工大学) International Digital Economy Academy (IDEA)(国际数字经济学院(IDEA))

专题命中 三维重建 :3D reconstruction(title,abstract);point cloud(abstract);分类 cs.CV

AI总结 SegVGGT通过端到端框架联合完成多视角图像的3D重建和实例分割,引入对象查询与多级几何特征交互,解决注意力分散问题,实验显示在ScanNetv2和ScanNet200上达到SOTA性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.17571 2026-03-19 cs.CV 83%

PanoVGGT: Feed-Forward 3D Reconstruction from Panoramic Imagery

PanoVGGT:从全景影像进行前馈3D重建

Yijing Guo, Mengjun Chao, Luo Wang, Tianyang Zhao, Haizhao Dai, Yingliang Zhang, Jingyi Yu, Yujiao Shi

机构 * ShanghaiTech University(上海科技大学) Sudo

专题命中 三维重建 :3D reconstruction(title,abstract);point cloud(abstract);分类 cs.CV

AI总结 本文提出PanoVGGT模型,通过单次前向传递从单或多张全景影像联合预测相机姿态、深度图和3D点云,采用球面感知位置嵌入和全景特定三轴SO(3)旋转增强,解决全局框架模糊问题,并贡献PanoCity大规模户外全景数据集。

Comments Accepted by CVPR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.15330 2026-03-17 cs.CV 83%

MeMix: Writing Less, Remembering More for Streaming 3D Reconstruction

MeMix:少写,多记:用于流式3D重建

Jiacheng Dong, Huan Li, Sicheng Zhou, Wenhao Hu, Weili Xu, Yan Wang

机构 * Institute for AI Industry Research, Tsinghua University(清华大学人工智能产业研究院) Zhejiang University(浙江大学)

专题命中 三维重建 :3D reconstruction(title,abstract);3D vision(abstract);分类 cs.CV

AI总结 MeMix通过将递归状态转化为记忆混合,提升流式3D重建性能,减少重建完整度误差,无需额外参数或微调。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.13556 2026-03-17 cs.CV cs.AI 83%

Semantic Aware Feature Extraction for Enhanced 3D Reconstruction

语义感知的特征提取用于增强3D重建

Ronald Nap, Andy Xiao

机构 * Department of Driving Assistance Systems(驾驶辅助系统系) Valeo(瓦莱奥)

专题命中 三维重建 :3D reconstruction(title,abstract);point cloud(abstract);分类 cs.CV

AI总结 本文提出一种结合关键点检测、描述和语义分割的多任务学习框架,用于提升3D重建的语义一致性与结构细节。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.12667 2026-03-16 cs.CV cs.AI eess.IV 83%

Marker-Based 3D Reconstruction of Aggregates with a Comparative Analysis of 2D and 3D Morphologies

基于标记的聚合物3D重建及其2D和3D形态的比较分析

Haohang Huang, Jiayi Luo, Issam Qamhia, Erol Tutumluer, John M. Hart, Andrew J. Stolba

专题命中 三维重建 :3D reconstruction(title,abstract);point cloud(abstract);分类 cs.CV

AI总结 本文提出一种基于摄影测量的低成本3D重建方法,通过标记设计实现背景抑制和点云拼接,用于获取聚合物的3D形态信息,对比2D和3D形态特性,验证了重建精度。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.01144 2026-03-09 cs.RO 83%

VISO: Robust Underwater Visual-Inertial-Sonar SLAM with Photometric Rendering for Dense 3D Reconstruction

VISO:具有光度渲染的鲁棒水下视觉-惯性-声纳SLAM用于密集3D重建

Shu Pan, Simon Archieri, Ahmet Cinar, Jonatan Scharff Willners, Ignacio Carlucho, Yvan Petillot

机构 * School of Engineering and Physical Sciences, Heriot-Watt University(工程与物理科学学院,赫瑞斯泰大学) Frontier Robotics, The National Robotarium(前沿机器人,国家机器人arium)

专题命中 三维重建 :3D reconstruction(title,abstract);point cloud(abstract);分类 cs.RO

AI总结 VISO通过融合视觉、惯性与声纳数据,结合光度渲染技术,实现高精度水下6自由度定位和实时密集3D重建。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.04179 2026-03-06 cs.CV 83%

NOVA3R: Non-pixel-aligned Visual Transformer for Amodal 3D Reconstruction

NOVA3R:非像素对齐的视觉变换器用于模态3D重建

Weirong Chen, Chuanxia Zheng, Ganlin Zhang, Andrea Vedaldi, Daniel Cremers

机构 * Technical University of Munich(慕尼黑技术大学) Munich Center for Machine Learning(慕尼黑机器学习中心) University of Oxford(牛津大学) Nanyang Technological University(南洋理工大学)

专题命中 三维重建 :3D reconstruction(title,abstract);point cloud(abstract);分类 cs.CV

AI总结 NOVA3R通过非像素对齐的视觉变换器实现更准确的3D重建,解决了传统像素对齐方法在处理可见和不可见点及重叠区域结构上的局限。

Comments Accepted to ICLR 2026. Project Page: https://wrchen530.github.io/nova3r

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.08862 2026-03-04 cs.CV cs.LG 83%

StreamSplat: Towards Online Dynamic 3D Reconstruction from Uncalibrated Video Streams

StreamSplat: 向动态3D重建的在线方法:从未校准视频流中

Zike Wu, Qi Yan, Xuanyu Yi, Lele Wang, Renjie Liao

机构 * University of British Columbia(不列颠哥伦比亚大学) Vector Institute for AI(人工智能向量研究所) Canada CIFAR AI Chair(加拿大CIFAR人工智能主席) Nanyang Technological University(南洋理工大学)

专题命中 三维重建 :3D reconstruction(title);Gaussian Splatting(abstract);3DGS(abstract);分类 cs.CV

AI总结 StreamSplat通过在线动态3D重建方法,实现从未校准视频流中快速生成高精度3DGS表示,支持任意长度视频的实时重建。

Comments Accepted by ICLR 2026, Project page: https://streamsplat3d.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.20160 2026-03-03 cs.CV 83%

tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction

tttLRM:面向长上下文和自回归3D重建的测试时间训练

Chen Wang, Hao Tan, Wang Yifan, Zhiqin Chen, Yuheng Liu, Kalyan Sunkavalli, Sai Bi, Lingjie Liu, Yiwei Hu

机构 * University of Pennsylvania(宾夕法尼亚大学) Adobe Research(Adobe 研究) UCI(加州大学欧文分校)

专题命中 三维重建 :3D reconstruction(title,abstract);novel view synthesis(abstract);分类 cs.CV

AI总结 tttLRM通过测试时间训练实现长上下文自回归3D重建,提升重建质量和收敛速度。

Comments Accepted by CVPR 2026. Project Page: https://cwchenwang.github.io/tttLRM

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.20718 2026-02-25 cs.CV 83%

Monocular Endoscopic Tissue 3D Reconstruction with Multi-Level Geometry Regularization

单目内窥镜组织三维重建与多级几何正则化

Yangsen Chen, Hao Wang

机构 * HKUST(GZ)(香港科技大学(珠海))

专题命中 三维重建 :3D reconstruction(title);NeRF(abstract);Gaussian Splatting(abstract);分类 cs.CV

AI总结 本文提出基于3D高斯点的单目内窥镜组织三维重建方法,结合多级几何正则化实现平滑表面与实时渲染。

Comments ijcnn 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.16950 2026-02-20 cs.CV 83%

HS-3D-NeRF: 3D Surface and Hyperspectral Reconstruction From Stationary Hyperspectral Images Using Multi-Channel NeRFs

HS-3D-NeRF:利用多通道NeRF实现从静态高光谱图像中重建3D表面和高光谱数据

Kibon Ku, Talukder Z. Jubery, Adarsh Krishnamurthy, Baskar Ganapathysubramanian

机构 * Iowa State University(爱荷华州立大学)

专题命中 三维重建 :NeRF(title,abstract);3D reconstruction(abstract);分类 cs.CV

AI总结 HS-3D-NeRF通过多通道NeRF实现静态高光谱图像的高吞吐量3D重建,用于农产品收获后的检查。

Comments 16 pages, 14 figures, 3 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.01035 2026-02-06 cs.CV 83%

FUSE-Flow: Scalable Real-Time Multi-View Point Cloud Reconstruction Using Confidence

FUSE-Flow:基于置信度的可扩展实时多视角点云重建

Chentian Sun

专题命中 三维重建 :point cloud(title,abstract);3D vision(abstract);分类 cs.CV

AI总结 FUSE-Flow通过自适应空间哈希加权聚合方法,实现高吞吐量低延迟的实时多视角点云重建,提升重建稳定性和几何保真度。

Comments A 5-page paper, prepared for submission to the 2026 IEEE International Conference on Image Processing (ICIP)

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.14552 2026-02-03 eess.IV cs.CV 83%

From Slices to Structures: Unsupervised 3D Reconstruction of Female Pelvic Anatomy from Freehand Transvaginal Ultrasound

从切片到结构:基于自由手经阴道超声的无监督3D女性盆腔解剖重建

Max Krähenmann, Sergio Tascon-Morales, Fabian Laumer, Julia E. Vogt, Ece Ozkan

机构 * ETH Zurich(苏黎世联邦理工学院) University of Basel(巴塞尔大学) Scanvio Medical AG(Scanvio医疗股份有限公司)

专题命中 三维重建 :3D reconstruction(title,abstract);Gaussian Splatting(abstract);分类 cs.CV

AI总结 本文提出TVGS方法,通过无监督学习从自由手经阴道超声图像实现高精度3D女性盆腔解剖重建,无需外部设备或姿态估计。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.00739 2026-02-03 cs.CV 83%

Diffusion-Driven Inter-Outer Surface Separation for Point Clouds with Open Boundaries

基于扩散的点云双层表面分离:用于开放边界

Zhengyan Qin, Liyuan Qiu

机构 * Hong Kong University of Science and Technology (HKUST)(香港理工大学) Hong Kong Applied Science and Technology Research Institute (ASTRI)(香港应用科技研究院)

专题命中 三维重建 :point cloud(title,abstract);3D reconstruction(abstract);分类 cs.CV

AI总结 本文提出了一种基于扩散的算法,用于分离双层点云的内层和外层表面,特别针对具有开放边界的点云,通过提取真实内层来解决重叠表面和法线紊乱问题。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.21459 2025-11-27 cs.GR 83%

Resolution Where It Counts: Hash-based GPU-Accelerated 3D Reconstruction via Variance-Adaptive Voxel Grids

关键区域的分辨率:基于哈希的GPU加速3D重建 via 变异自适应体素网格

Lorenzo De Rebotti, Emanuele Giacomini, Giorgio Grisetti, Luca Di Giammarino

专题命中 三维重建 :3D reconstruction(title,abstract);Gaussian Splatting(abstract);分类 cs.GR

AI总结 本文提出一种基于哈希的GPU加速3D重建方法,通过变异自适应体素网格实现高内存效率和实时可扩展性,相比传统方法提升了性能并保持重建精度。

Comments Accepted for publication in ACM Transaction on Graphics. Project site: https://rvp-group.github.io/mrhash/

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.20343 2025-11-26 cs.CV 83%

AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend

AMB3R: 基于后端的精确前馈度量尺度3D重建

Hengyi Wang, Lourdes Agapito

机构 * Department of Computer Science, University College London(计算机科学系,伦敦大学学院)

专题命中 三维重建 :3D reconstruction(title,abstract);3D vision(abstract);分类 cs.CV

AI总结 AMB3R通过稀疏体素表示实现高精度度量尺度3D重建,可扩展至视觉里程计和大尺度结构从运动,超越传统SLAM和SfM方法。

Comments Project page: https://hengyiwang.github.io/projects/amber

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.08545 2025-11-12 cs.CV 83%

RePose-NeRF: Robust Radiance Fields for Mesh Reconstruction under Noisy Camera Poses

Sriram Srinivasan, Gautam Ramachandra

机构 * Bellatrix Aerospace(贝尔拉克斯航空航天)

专题命中 三维重建 :NeRF(title,abstract);3D reconstruction(abstract);分类 cs.CV

Comments Several figures are included to illustrate the reconstruction and rendering quality of the proposed method, which is why the submission exceeds the 50MB file size limit. > Several figures are included to illustrate the reconstruction and rendering quality of the proposed method, which is why the submission exceeds the 50,000 KB file size limit (Now this has been resolved)

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.08894 2025-11-04 cs.CV 83%

OpenMaterial: A Large-scale Dataset of Complex Materials for 3D Reconstruction

Zheng Dang, Jialu Huang, Fei Wang, Mathieu Salzmann

机构 * CVLab, EPFL, Switzerland(苏黎世联邦理工学院计算机视觉实验室) Xi’an Jiaotong University, China(西安交通大学)

专题命中 三维重建 :3D reconstruction(title,abstract);novel view synthesis(abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.22706 2025-11-03 cs.CV 83%

IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction

Hao Li, Zhengyu Zou, Fangfu Liu, Xuanyang Zhang, Fangzhou Hong, Yukang Cao, Yushi Lan, Manyuan Zhang, Gang Yu, Dingwen Zhang, Ziwei Liu

机构 * NWPU(西北工业大学) S-Lab, NTU(NTU实验室) StepFun, Inc.(StepFun公司) THU(清华大学) MMLab, CUHK(CUHK实验室)

专题命中 三维重建 :3D reconstruction(title,abstract);spatial understanding(abstract);分类 cs.CV

Comments https://github.com/lifuguan/IGGT_official

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.14798 2025-10-27 cs.CV 83%

An Evaluation of DUSt3R/MASt3R/VGGT 3D Reconstruction on Photogrammetric Aerial Blocks

Xinyi Wu, Steven Landgraf, Markus Ulrich, Rongjun Qin

专题命中 三维重建 :3D reconstruction(title,abstract);point cloud(abstract);分类 cs.CV

Comments 23 pages, 7 figures, this manuscript has been submitted to Geo-spatial Information Science for consideration

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.16050 2025-09-22 cs.CV 83%

Graph-based Point Cloud Surface Reconstruction using B-Splines

Stuti Pathak, Rhys G. Evans, Gunther Steenackers, Rudi Penne

机构 * University of Antwerp(安特卫普大学)

专题命中 三维重建 :point cloud(title,abstract);3D vision(abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.15242 2025-09-22 cs.CV 83%

ProFusion: 3D Reconstruction of Protein Complex Structures from Multi-view AFM Images

Jaydeep Rade, Md Hasibul Hasan Hasib, Meric Ozturk, Baboucarr Faal, Sheng Yang, Dipali G. Sashital, Vincenzo Venditti, Baoyu Chen, Soumik Sarkar, Adarsh Krishnamurthy, Anwesha Sarkar

机构 * Department of Electrical and Computer Engineering, Iowa State University(电气与计算机工程系,爱荷华州立大学) Department of Mechanical Engineering, Iowa State University(机械工程系,爱荷华州立大学) Roy J. Carver Department of Biochemistry, Biophysics and Molecular Biology, Iowa State University(罗伊·J·卡弗生物化学、生物物理和分子生物学系,爱荷华州立大学) Target & Protein Sciences, Janssen R&D, Johnson & Johnson(贾尼斯森研发部,强生公司) Department of Chemistry, Iowa State University(化学系,爱荷华州立大学) Departments of Internal Medicine and Biophysics, University of Texas Southwestern Medical Center(内科学与生物物理学系,德克萨斯西南医学中心)

专题命中 三维重建 :3D reconstruction(title,abstract);NeRF(abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.16433 2025-08-25 cs.CV 83%

HAMSt3R: Human-Aware Multi-view Stereo 3D Reconstruction

Sara Rojas, Matthieu Armando, Bernard Ghamen, Philippe Weinzaepfel, Vincent Leroy, Gregory Rogez

机构 * KAUST(科威特科学与技术王国) NAVER LABS Europe(NAVER欧洲实验室)

专题命中 三维重建 :3D reconstruction(title,abstract);3D vision(abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.15811 2025-08-13 cs.CV 83%

PointDreamer: Zero-shot 3D Textured Mesh Reconstruction from Colored Point Cloud

Qiao Yu, Xianzhi Li, Yuan Tang, Xu Han, Jinfeng Xu, Long Hu, Min Chen

机构 * Huazhong University of Science and Technology(华中科技大学) School of Computer Science and Technology(计算机科学与技术学院) Guangdong HUST Industrial Technology Research Institute(广东华中科技大学产业技术研究院) School of Computer Science and Engineering(计算机科学与工程学院) South China University of Technology(华南理工大学) Pazhou Laboratory(琶洲实验室)

专题命中 三维重建 :point cloud(title,abstract);3D reconstruction(abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.03118 2025-08-06 cs.CV 83%

H3R: Hybrid Multi-view Correspondence for Generalizable 3D Reconstruction

Heng Jia, Linchao Zhu, Na Zhao

机构 * ReLER Lab, CCAI, Zhejiang University(浙江大学ReLER实验室,中国计算机协会,浙江大学) The State Key Lab of Brain-Machine Intelligence, Zhejiang University(浙江大学脑机智能国家重点实验室) Singapore University of Technology and Design(新加坡科技设计大学)

专题命中 三维重建 :3D reconstruction(title,abstract);Gaussian Splatting(abstract);分类 cs.CV

Comments ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.01647 2025-08-06 cs.CV 83%

FlowR: Flowing from Sparse to Dense 3D Reconstructions

Tobias Fischer, Samuel Rota Bulò, Yung-Hsu Yang, Nikhil Keetha, Lorenzo Porzi, Norman Müller, Katja Schwarz, Jonathon Luiten, Marc Pollefeys, Peter Kontschieder

机构 * ETH Zürich(苏黎世联邦理工学院) Meta Reality Labs Zürich(Meta现实实验室(苏黎世)) CMU(卡内基梅隆大学)

专题命中 三维重建 :3D reconstruction(title);Gaussian Splatting(abstract);novel view synthesis(abstract);分类 cs.CV

Comments ICCV 2025 Highlight. Project page is available at https://tobiasfshr.github.io/pub/flowr

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.18292 2025-08-04 cs.CV 83%

Three-dimentional reconstruction of complex, dynamic population canopy architecture for crops with a novel point cloud completion model: A case study in Brassica napus rapeseed

Ziyue Guo, Xin Yang, Yutao Shen, Yang Zhu, Lixi Jiang, Haiyan Cen

专题命中 三维重建 :point cloud(title,abstract);3D reconstruction(abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2407.15228 2025-07-15 cs.CV 83%

3D Reconstruction of the Human Colon from Capsule Endoscope Video

Pål Anders Floor, Ivar Farup, Marius Pedersen

机构 * Colourlab, Department of Computer Science, Norwegian University of Science and Technology (NTNU)(色彩实验室,计算机科学系,挪威科学技术大学)

专题命中 三维重建 :3D reconstruction(title,abstract);point cloud(abstract);分类 cs.CV

Comments 11 pages, 12 figures

Journal ref IEEE ACCESS, Volume 13, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.07410 2025-07-11 cs.CV 83%

EscherNet++: Simultaneous Amodal Completion and Scalable View Synthesis through Masked Fine-Tuning and Enhanced Feed-Forward 3D Reconstruction

Xinan Zhang, Muhammad Zubair Irshad, Anthony Yezzi, Yi-Chang Tsai, Zsolt Kira

机构 * Georgia Institute of Technology(佐治亚理工学院) Toyota Research Institute(丰田研究机构)

专题命中 三维重建 :3D reconstruction(title,abstract);novel view synthesis(abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏