视觉与机器人

3D 视觉

三维重建、NeRF、Gaussian Splatting、点云和空间智能。

2025-10-02 至 2025-10-02 共收录 3 篇信号源：cs.CV, cs.GR, cs.RO

1. 点云 3 篇

2509.15935 2025-10-02 cs.CV 57%

PAN: Pillars-Attention-Based Network for 3D Object Detection

Ruan Bispo, Dane Mitrev, Letizia Mariotti, Clément Botty, Denver Humphrey, Anthony Scanlan, Ciarán Eising

机构 * Department of Electronic and Computer Engineering, Lero (the Research Ireland Centre for Software), and the Data Driven Computer Engineering (D 2 iCE) Research Centre at the University of Limerick（电子与计算机工程系，Lero（爱尔兰软件研究中心），以及利默里克大学数据驱动计算机工程（D 2 iCE）研究中心）； Provizio, Future Mobility Campus Ireland, Shannon Free Zone（Provizio，Future Mobility Campus Ireland，Shannon Free Zone）

专题命中点云：point cloud(abstract)；分类 cs.CV

2503.24391 2025-10-02 cs.CV 57%

Easi3R: Estimating Disentangled Motion from DUSt3R Without Training

Xingyu Chen, Yue Chen, Yuliang Xiu, Andreas Geiger, Anpei Chen

机构 * Zhejiang University（浙江大学）； Westlake University（西湖大学）； Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）； University of Tübingen, Tübingen AI Center（图宾根大学，图宾根AI中心）

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Page: https://easi3r.github.io/ Code: https://github.com/Inception3D/Easi3R

Journal ref IEEE/CVF International Conference on Computer Vision (ICCV), 2025

2510.00746 2025-10-02 math.DG math.OC 50%

Approximate mean curvature flows of a general varifold, and their limit spacetime Brakke flow

Blanche Buet, Gian Paolo Leonardi, Simon Masnou, Abdelmouksit Sagueni

专题命中点云：point cloud(abstract)