3D 视觉 - arXivDaily 专题

2512.17781 2026-03-20 cs.CV cs.GR 73%

LiteGE: Lightweight Geodesic Embedding for Efficient Geodesics Computation and Non-Isometric Shape Correspondence

LiteGE：轻量级测地嵌入用于高效测地线计算和非等距形状对应

Yohanes Yudhi Adikusuma, Qixing Huang, Ying He

专题命中三维重建：3D vision(abstract)；point cloud(abstract)；分类 cs.CV、cs.GR

AI总结 LiteGE通过PCA处理信息体素的无符号距离场样本，构建紧凑且类别感知的形状描述符，实现高效测地线计算和非等距形状对应，显著降低内存使用和推理时间。

Journal ref Proceedings of the 40th AAAI Conference on Artificial Intelligence (AAAI-26), 2026

2510.02691 2026-03-20 cs.CV cs.GR 73%

FSFSplatter: Build Surface and Novel Views with Sparse-Views within 2min

FSFSplatter: 用稀疏视图在2分钟内构建表面和新视角

Yibin Zhao, Yihan Pan, Jun Nan, Liwei Chen, Jianjun Yi

机构 * East China University of Science and Technology, Shanghai（东华大学上海理工学院）； Shanghai Xiaoyuan Innovation Center, Shanghai（上海小元创新中心）

专题命中三维重建：Gaussian Splatting(abstract)；novel view synthesis(abstract)；分类 cs.CV、cs.GR

AI总结本文提出FSFSplatter方法，通过端到端的密集高斯初始化、相机参数估计和几何增强场景优化，实现从自由稀疏图像快速重建表面和新视角，优于现有最先进方法。

2601.17733 2026-01-27 cs.CV cs.GR 73%

Flatten The Complex: Joint B-Rep Generation via Compositional $k$-Cell Particles

扁平化复杂：通过组合k-cell粒子进行联合B-Rep生成

Junran Lu, Yuanqi Li, Hengji Li, Jie Guo, Yanwen Guo

机构 * Nanjing University（南京大学）

专题命中三维重建：3D reconstruction(abstract)；point cloud(abstract)；分类 cs.CV、cs.GR

AI总结本文提出了一种基于组合k-cell粒子的B-Rep生成方法，通过解耦层次结构实现拓扑与几何的联合生成，提升生成模型的精度和可编辑性。

2512.08930 2025-12-23 cs.CV cs.GR 73%

Selfi: Self Improving Reconstruction Engine via 3D Geometric Feature Alignment

Selfi: 通过3D几何特征对齐实现自改进的重建引擎

Youming Deng, Songyou Peng, Junyi Zhang, Kathryn Heal, Tiancheng Sun, John Flynn, Steve Marschner, Lucy Chai

机构 * Cornell University（康奈尔大学）； Google（谷歌）； UC Berkeley（加州大学伯克利分校）

专题命中三维重建：3D reconstruction(abstract)；novel view synthesis(abstract)；分类 cs.CV、cs.GR

AI总结 Selfi通过特征对齐提升3D重建精度，利用VGGT输出作为伪地面真实值，实现NVS和姿态估计的高性能表现。

Comments Project Page: https://denghilbert.github.io/selfi/

2511.07206 2025-11-11 cs.CV cs.CG cs.GR 73%

Geometric implicit neural representations for signed distance functions

Luiz Schirmer, Tiago Novello, Vinícius da Silva, Guilherme Schardong, Daniel Perazzo, Hélio Lopes, Nuno Gonçalves, Luiz Velho

专题命中三维重建：3D reconstruction(abstract)；point cloud(abstract)；分类 cs.CV、cs.GR

2509.12458 2025-10-22 cs.RO cs.AR cs.CV cs.ET cs.SY eess.SY 73%

Neural 3D Object Reconstruction with Small-Scale Unmanned Aerial Vehicles

Àlmos Veres-Vitàlyos, Genis Castillo Gomez-Raya, Filip Lemic, Daniel Johannes Bugelnig, Bernhard Rinner, Sergi Abadal, Xavier Costa-Pérez

机构 * i2CAT Foundation（i2CAT基金会）； University of Klagenfurt（克雷格弗特大学）； Universitat Politècnica de Catalunya（巴塞罗那理工大学）； Faculty of Electrical Engineering and Computing（电气工程与计算学院）； University of Zagreb（扎格雷布大学）； NEC Labs Europe GmbH（NEC欧洲实验室）； ICREA

专题命中三维重建：NeRF(abstract)；3D reconstruction(abstract)；分类 cs.CV、cs.RO

Comments 13 pages, 16 figures, 3 tables, 45 references

2509.20401 2025-10-17 cs.CV cs.RO 73%

SGAligner++: Cross-Modal Language-Aided 3D Scene Graph Alignment

Binod Singh, Sayan Deb Sarkar, Iro Armeni

机构 * Technical University of Munich（慕尼黑技术大学）； Stanford University（斯坦福大学）

专题命中三维重建：3D reconstruction(abstract)；point cloud(abstract)；分类 cs.CV、cs.RO

Comments Project Page: https://singhbino3d.github.io/sgpp/

2508.21344 2025-09-30 cs.GR cs.CV 73%

ARGS: Advanced Regularization on Aligning Gaussians over the Surface

Jeong Uk Lee, Sung Hee Choi

机构 * KAIST（韩国科学技术院）

专题命中三维重建：Gaussian Splatting(abstract)；3DGS(abstract)；分类 cs.CV、cs.GR

Comments 9 pages, 4 figures

2412.03526 2025-09-23 cs.CV cs.AI cs.GR 73%

Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos

Hanxue Liang, Jiawei Ren, Ashkan Mirzaei, Antonio Torralba, Ziwei Liu, Igor Gilitschenski, Sanja Fidler, Cengiz Oztireli, Huan Ling, Zan Gojcic, Jiahui Huang

专题命中三维重建：Gaussian Splatting(abstract)；novel view synthesis(abstract)；分类 cs.CV、cs.GR

Comments Project website: https://research.nvidia.com/labs/toronto-ai/bullet-timer/

2509.02474 2025-09-03 cs.GR cs.CV cs.LG 73%

Unifi3D: A Study on 3D Representations for Generation and Reconstruction in a Common Framework

Nina Wiedemann, Sainan Liu, Quentin Leboutet, Katelyn Gao, Benjamin Ummenhofer, Michael Paulitsch, Kai Yuan

机构 * Intel Corporation（英特尔公司）

专题命中三维重建：point cloud(abstract)；3D generation(abstract)；分类 cs.CV、cs.GR

2504.19938 2025-08-26 cs.CV cs.RO 73%

Mesh-Learner: Texturing Mesh with Spherical Harmonics

Yunfei Wan, Jianheng Liu, Chunran Zheng, Jiarong Lin, Fu Zhang

机构 * Department of Mechanical Engineering, The University of Hong Kong（机械工程系，香港大学）

专题命中三维重建：Gaussian Splatting(abstract)；3D reconstruction(abstract)；分类 cs.CV、cs.RO

Comments IROS2025 Accepted

2502.00360 2025-08-19 cs.CV cs.GR 73%

Shape from Semantics: 3D Shape Generation from Multi-View Semantics

Liangchen Li, Caoliwen Wang, Yuqi Zhou, Bailin Deng, Juyong Zhang

机构 * University of Science and Technology of China（科学技术大学）； Cardiff University（卡地夫大学）

专题命中三维重建：3D reconstruction(abstract)；point cloud(abstract)；分类 cs.CV、cs.GR

Comments Project page: https://shapefromsemantics.github.io

2503.19976 2025-03-27 cs.GR cs.CV cs.LG 73%

Thin-Shell-SfT: Fine-Grained Monocular Non-rigid 3D Surface Tracking with Neural Deformation Fields

Navami Kairanda, Marc Habermann, Shanthika Naik, Christian Theobalt, Vladislav Golyanik

机构 * MPI for Informatics（马克斯·普朗克信息学研究所）； VIA Research Center（VIA研究中心）； IIT Jodhpur（焦特布尔印度理工学院）

专题命中三维重建：Gaussian Splatting(abstract)；3D reconstruction(abstract)；分类 cs.CV、cs.GR

Comments 15 pages, 12 figures and 3 tables; project page: https://4dqv.mpiinf.mpg.de/ThinShellSfT; CVPR 2025

2404.12385 2025-01-24 cs.CV cs.GR 73%

MeshLRM: Large Reconstruction Model for High-Quality Meshes

Xinyue Wei, Kai Zhang, Sai Bi, Hao Tan, Fujun Luan, Valentin Deschaintre, Kalyan Sunkavalli, Hao Su, Zexiang Xu

机构 * University of California San Diego（加州大学圣迭戈分校）； Adobe Research（奥多比研究院）

专题命中三维重建：NeRF(abstract)；3D generation(abstract)；分类 cs.CV、cs.GR

2501.10474 2025-01-22 cs.GR cs.CV 73%

Poxel: Voxel Reconstruction for 3D Printing

Ruixiang Cao, Satoshi Yagi, Satoshi Yamamori, Jun Morimoto

机构 * Graduate School of Informatics, Kyoto University（京都大学信息学研究科）； ATR（高级电信研究所）

专题命中三维重建：NeRF(abstract)；3D reconstruction(abstract)；分类 cs.CV、cs.GR

2412.07746 2024-12-11 cs.CV cs.LG cs.RO 73%

LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation Models

Ziqi Lu, Heng Yang, Danfei Xu, Boyi Li, Boris Ivanovic, Marco Pavone, Yue Wang

专题命中三维重建：3D vision(abstract)；3D reconstruction(abstract)；分类 cs.CV、cs.RO

2412.00845 2024-12-03 cs.CV cs.GR 73%

SAGA: Surface-Aligned Gaussian Avatar

Ronghan Chen, Yang Cong, Jiayue Liu

专题命中三维重建：NeRF(abstract)；3DGS(abstract)；分类 cs.CV、cs.GR

Comments Submitted to TPAMI. Major Revision. Project page: https://gostinshell.github.io/SAGA/

2411.19548 2024-12-02 cs.CV cs.AI cs.LG cs.RO 73%

ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration

Chaojun Ni, Guosheng Zhao, Xiaofeng Wang, Zheng Zhu, Wenkang Qin, Guan Huang, Chen Liu, Yuyin Chen, Yida Wang, Xueyang Zhang, Yifei Zhan, Kun Zhan, Peng Jia, Xianpeng Lang, Xingang Wang, Wenjun Mei

专题命中三维重建：NeRF(abstract)；3DGS(abstract)；分类 cs.CV、cs.RO

Comments Project Page: https://recondreamer.github.io

2409.19405 2024-10-01 cs.CV cs.RO 73%

G3R: Gradient Guided Generalizable Reconstruction

Yun Chen, Jingkang Wang, Ze Yang, Sivabalan Manivasagam, Raquel Urtasun

专题命中三维重建：NeRF(abstract)；3DGS(abstract)；分类 cs.CV、cs.RO

Comments ECCV 2024. Project page: https://waabi.ai/g3r

2409.05310 2024-09-10 cs.RO cs.CV 73%

Neural Surface Reconstruction and Rendering for LiDAR-Visual Systems

Jianheng Liu, Chunran Zheng, Yunfei Wan, Bowen Wang, Yixi Cai, Fu Zhang

专题命中三维重建：NeRF(abstract)；point cloud(abstract)；分类 cs.CV、cs.RO

2409.02376 2024-09-05 cs.CV cs.AI cs.GR cs.HC cs.MM 73%

Coral Model Generation from Single Images for Virtual Reality Applications

Jie Fu, Shun Fu, Mick Grierson

专题命中三维重建：3D vision(abstract)；3D reconstruction(abstract)；分类 cs.CV、cs.GR

Comments In Proceedings of Explainable AI for the Arts Workshop 2024 (XAIxArts 2024) arXiv:2406.14485

2408.10195 2024-08-20 cs.CV cs.AI cs.GR 73%

SpaRP: Fast 3D Object Reconstruction and Pose Estimation from Sparse Views

Chao Xu, Ang Li, Linghao Chen, Yulin Liu, Ruoxi Shi, Hao Su, Minghua Liu

专题命中三维重建：3D reconstruction(abstract)；3D generation(abstract)；分类 cs.CV、cs.GR

Comments ECCV 2024

2312.08744 2024-07-16 cs.CV cs.GR 73%

GOEmbed: Gradient Origin Embeddings for Representation Agnostic 3D Feature Learning

Animesh Karnewar, Roman Shapovalov, Tom Monnier, Andrea Vedaldi, Niloy J. Mitra, David Novotny

专题命中三维重建：3D reconstruction(abstract)；3D generation(abstract)；分类 cs.CV、cs.GR

Comments ECCV 2024 conference; project page at: https://holodiffusion.github.io/goembed/

2311.04400 2024-03-12 cs.CV cs.AI cs.GR cs.LG 73%

LRM: Large Reconstruction Model for Single Image to 3D

Yicong Hong, Kai Zhang, Jiuxiang Gu, Sai Bi, Yang Zhou, Difan Liu, Feng Liu, Kalyan Sunkavalli, Trung Bui, Hao Tan

专题命中三维重建：NeRF(abstract)；3D reconstruction(abstract)；分类 cs.CV、cs.GR

Comments ICLR 2024

2402.17115 2024-02-28 cs.CV cs.GR 73%

CharNeRF: 3D Character Generation from Concept Art

Eddy Chu, Yiyang Chen, Chedy Raissi, Anand Bhojan

专题命中三维重建：NeRF(abstract)；3D reconstruction(abstract)；分类 cs.CV、cs.GR

2303.07997 2023-03-15 cs.RO cs.AI cs.CV 73%

FingerSLAM: Closed-loop Unknown Object Localization and Reconstruction from Visuo-tactile Feedback

Jialiang Zhao, Maria Bauza, Edward H. Adelson

专题命中三维重建：3D reconstruction(abstract)；point cloud(abstract)；分类 cs.CV、cs.RO

Comments Submitted and accepted to 2023 IEEE International Conference on Robotics and Automation (ICRA 2023)

2211.08634 2022-11-17 cs.RO cs.CV 73%

Semantic keypoint extraction for scanned animals using multi-depth-camera systems

Raphael Falque, Teresa Vidal-Calleja, Alen Alempijevic

专题命中三维重建：3D reconstruction(abstract)；point cloud(abstract)；分类 cs.CV、cs.RO

2209.08221 2022-09-20 cs.CV cs.RO 73%

Neural Implicit Surface Reconstruction using Imaging Sonar

Mohamad Qadri, Michael Kaess, Ioannis Gkioulekas

专题命中三维重建：3D reconstruction(abstract)；point cloud(abstract)；分类 cs.CV、cs.RO

Comments 8 pages, 8 figures. This paper is under review

2107.04286 2022-07-20 cs.CV cs.GR 73%

Capturing, Reconstructing, and Simulating: the UrbanScene3D Dataset

Liqiang Lin, Yilin Liu, Yue Hu, Xingguang Yan, Ke Xie, Hui Huang

专题命中三维重建：3D reconstruction(abstract)；point cloud(abstract)；分类 cs.CV、cs.GR

Comments ECCV 2022 camera ready; Project page: https://vcc.tech/UrbanScene3D/

2206.08365 2022-06-17 cs.CV cs.RO 73%

Virtual Correspondence: Humans as a Cue for Extreme-View Geometry

Wei-Chiu Ma, Anqi Joyce Yang, Shenlong Wang, Raquel Urtasun, Antonio Torralba

专题命中三维重建：3D reconstruction(abstract)；novel view synthesis(abstract)；分类 cs.CV、cs.RO

Comments CVPR 2022. Project page: https://people.csail.mit.edu/weichium/virtual-correspondence/

1. 三维重建 4401 篇

LiteGE: Lightweight Geodesic Embedding for Efficient Geodesics Computation and Non-Isometric Shape Correspondence

FSFSplatter: Build Surface and Novel Views with Sparse-Views within 2min

Flatten The Complex: Joint B-Rep Generation via Compositional $k$-Cell Particles

Selfi: Self Improving Reconstruction Engine via 3D Geometric Feature Alignment

Geometric implicit neural representations for signed distance functions

Neural 3D Object Reconstruction with Small-Scale Unmanned Aerial Vehicles

SGAligner++: Cross-Modal Language-Aided 3D Scene Graph Alignment

ARGS: Advanced Regularization on Aligning Gaussians over the Surface

Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos

Unifi3D: A Study on 3D Representations for Generation and Reconstruction in a Common Framework

Mesh-Learner: Texturing Mesh with Spherical Harmonics

Shape from Semantics: 3D Shape Generation from Multi-View Semantics

Thin-Shell-SfT: Fine-Grained Monocular Non-rigid 3D Surface Tracking with Neural Deformation Fields

MeshLRM: Large Reconstruction Model for High-Quality Meshes

Poxel: Voxel Reconstruction for 3D Printing

LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation Models

SAGA: Surface-Aligned Gaussian Avatar

ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration

G3R: Gradient Guided Generalizable Reconstruction

Neural Surface Reconstruction and Rendering for LiDAR-Visual Systems

Coral Model Generation from Single Images for Virtual Reality Applications

SpaRP: Fast 3D Object Reconstruction and Pose Estimation from Sparse Views

GOEmbed: Gradient Origin Embeddings for Representation Agnostic 3D Feature Learning

LRM: Large Reconstruction Model for Single Image to 3D

CharNeRF: 3D Character Generation from Concept Art

FingerSLAM: Closed-loop Unknown Object Localization and Reconstruction from Visuo-tactile Feedback

Semantic keypoint extraction for scanned animals using multi-depth-camera systems

Neural Implicit Surface Reconstruction using Imaging Sonar

Capturing, Reconstructing, and Simulating: the UrbanScene3D Dataset

Virtual Correspondence: Humans as a Cue for Extreme-View Geometry