视觉与机器人

3D 视觉

三维重建、NeRF、Gaussian Splatting、点云和空间智能。

2025-10-29 至 2025-10-29 共收录 8 篇信号源：cs.CV, cs.GR, cs.RO

1. 三维重建 2 篇

2510.22118 2025-10-29 cs.CV cs.AI 57%

GRAID: Enhancing Spatial Reasoning of VLMs Through High-Fidelity Data Generation

Karim Elmaaroufi, Liheng Lai, Justin Svegliato, Yutong Bai, Sanjit A. Seshia, Matei Zaharia

机构 * University of California, Berkeley（加州大学伯克利分校）； Models for Embodied and Spatial Harmony（具身与空间和谐模型）

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

Comments 22 pages, 3 figures, 3 tables, project page: https://ke7.github.io/graid/

2510.24648 2025-10-29 physics.optics 50%

Toward Photon-Induced Near-Field Electron Tomography

Tamir Shpiro, Ron Ruimy, Qinghui Yan, Tomer Bucher, Avner Shultzman, Hanan Herzig Sheinfux, Ido Kaminer

专题命中三维重建：3D reconstruction(abstract)

2. Gaussian Splatting 2 篇

2510.23988 2025-10-29 cs.RO 83%

A Survey on Collaborative SLAM with 3D Gaussian Splatting

Phuc Nguyen Xuan, Thanh Nguyen Canh, Huu-Hung Nguyen, Nak Young Chong, Xiem HoangVan

机构 * Institute of System Integration, Le Quy Don Technical University, Hanoi, 10000, Vietnam（越南吕文技术大学系统整合研究所）； Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology（日本先进科学技术研究院先进科学技术研究生院）； University of Engineering and Technology, Vietnam National University, Hanoi, 10000, Vietnam（越南国家大学工程技术大学）

专题命中 Gaussian Splatting ：Gaussian Splatting(title,abstract)；3DGS(abstract)；分类 cs.RO

2510.23930 2025-10-29 cs.CV 83%

PlanarGS: High-Fidelity Indoor 3D Gaussian Splatting Guided by Vision-Language Planar Priors

Xirui Jin, Renbiao Jin, Boying Li, Danping Zou, Wenxian Yu

机构 * Shanghai Jiao Tong University（上海交通大学）； Monash University（墨尔本大学）

专题命中 Gaussian Splatting ：Gaussian Splatting(title,abstract)；3DGS(abstract)；分类 cs.CV

Comments Accepted by NeurIPS 2025. Project page: https://planargs.github.io

3. 点云 2 篇

2510.20974 2025-10-29 cs.RO cs.LG 79%

Robust Point Cloud Reinforcement Learning via PCA-Based Canonicalization

Michael Bezick, Vittorio Giammarino, Ahmed H. Qureshi

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

2509.20077 2025-10-29 cs.RO cs.CV cs.HC 62%

Queryable 3D Scene Representation: A Multi-Modal Framework for Semantic Reasoning and Robotic Task Planning

Xun Li, Rodrigo Santa Cruz, Mingze Xi, Hu Zhang, Madhawa Perera, Ziwei Wang, Ahalya Ravendran, Brandon J. Matthews, Feng Xu, Matt Adcock, Dadong Wang, Jiajun Liu

机构 * CSIRO（澳大利亚联邦科学与工业研究组织）

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

Journal ref MM '25: Proceedings of the 33rd ACM International Conference on Multimedia (2025) Pages 12492 - 12500

4. 新视角合成 1 篇

2510.24335 2025-10-29 cs.RO cs.CV 81%

NVSim: Novel View Synthesis Simulator for Large Scale Indoor Navigation

Mingyu Jeong, Eunsung Kim, Sehun Park, Andrew Jaeyong Choi

专题命中新视角合成：novel view synthesis(title)；Gaussian Splatting(abstract)；分类 cs.CV、cs.RO

Comments 9 pages, 10 figures

5. 空间理解 1 篇

2510.24706 2025-10-29 cs.CL cs.AI cs.HC cs.SE 50%

ComboBench: Can LLMs Manipulate Physical Devices to Play Virtual Reality Games?

Shuqing Li, Jiayi Yan, Chenyu Niu, Jen-tse Huang, Yun Peng, Wenxuan Wang, Yepang Liu, Michael R. Lyu

机构 * Chinese University of Hong Kong（香港中文大学）； Southern University of Science and Technology（南方科技大学）

专题命中空间理解：spatial understanding(abstract)