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 9 篇信号源：cs.CV, cs.GR, cs.RO

1. 三维重建 3 篇

2510.01183 2025-10-02 cs.CV 57%

EvoWorld: Evolving Panoramic World Generation with Explicit 3D Memory

Jiahao Wang, Luoxin Ye, TaiMing Lu, Junfei Xiao, Jiahan Zhang, Yuxiang Guo, Xijun Liu, Rama Chellappa, Cheng Peng, Alan Yuille, Jieneng Chen

机构 * Johns Hopkins University（约翰霍普金斯大学）

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

Comments Code available at: https://github.com/JiahaoPlus/EvoWorld

2409.10836 2025-10-02 cs.CV 57%

SL$^{2}$A-INR: Single-Layer Learnable Activation for Implicit Neural Representation

Moein Heidari, Reza Rezaeian, Reza Azad, Dorit Merhof, Hamid Soltanian-Zadeh, Ilker Hacihaliloglu

机构 * University of British Columbia（不列颠哥伦比亚大学）； University of Tehran（塔里斯坦大学）； RWTH Aachen University（亚琛工业大学）； University of Regensburg（莱茵河畔大学）

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

Comments Accepted to ICCV 2025

2503.13802 2025-10-02 math.NA cs.NA 50%

Multi-Harmonic Gridded 3D Deconvolution (MH3D) for Robust and Accurate Image Reconstruction in MPI for Single Axis Drive Field Scanners

Toby Sanders, Justin J. Konkle, Erica E. Mason, Patrick W. Goodwill

专题命中三维重建：3D reconstruction(abstract)

2. NeRF 1 篇

2510.00592 2025-10-02 cs.CV 70%

Multi-level Dynamic Style Transfer for NeRFs

Zesheng Li, Shuaibo Li, Wei Ma, Jianwei Guo, Hongbin Zha

专题命中 NeRF ：3D vision(abstract)；NeRF(abstract)；分类 cs.CV

Comments Accepted by Computational Visual Media Journal (CVMJ)

3. Gaussian Splatting 1 篇

2510.01119 2025-10-02 cs.CV 74%

Instant4D: 4D Gaussian Splatting in Minutes

Zhanpeng Luo, Haoxi Ran, Li Lu

机构 * University of Pittsburgh（匹兹堡大学）； Carnegie Mellon University（卡内基梅隆大学）

专题命中 Gaussian Splatting ：Gaussian Splatting(title)；分类 cs.CV

Comments Accepted by NeurIPS 25

4. 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)

5. SLAM与定位 1 篇

2510.00527 2025-10-02 cs.CV 57%

Cascaded Diffusion Framework for Probabilistic Coarse-to-Fine Hand Pose Estimation

Taeyun Woo, Jinah Park, Tae-Kyun Kim

机构 * KAIST（韩国科学技术院）

专题命中 SLAM与定位：3D reconstruction(abstract)；分类 cs.CV

Comments 15 pages, 8 figures