视觉与机器人

3D 视觉

三维重建、NeRF、Gaussian Splatting、点云和空间智能。

2026-04-15 至 2026-04-15 共收录 2 篇信号源：cs.CV, cs.GR, cs.RO

1. 三维重建 2 篇

2604.12894 2026-04-15 cs.CV 57%

Representing 3D Faces with Learnable B-Spline Volumes

用可学习的B样条体积表示3D人脸

Prashanth Chandran, Daoye Wang, Timo Bolkart

机构 * Google（谷歌）

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

AI总结本文提出CUBE方法，结合B样条体积与学习特征，用于3D扫描配准和单目3D人脸重建，通过高维控制特征提升模型表达能力，实现局部表面编辑。

Comments Accepted to CVPR 2026 (Highlight)

2604.12466 2026-04-15 eess.SP 50%

RIS-Aided Sensing: Experimental Validation of Radar 3D Imaging in the mmWave Band

利用RIS的传感：毫米波带雷达三维成像的实验验证

Sergio Micó-Rosa, Alvaro Villaescusa-Tebar, Saúl Fenollosa, Carlos Villena-Jiménez, Monika Drozdowska, Narcis Cardona

专题命中三维重建：3D reconstruction(abstract)

AI总结本文通过实验验证了结合FMCW雷达和1位RIS的毫米波三维成像框架，实现了自主化的三维重建，展示了在不同场景下的高精度目标识别能力。

Comments 7 pages, 7 figures, 3 tables. This work has been accepted for publication in 2026 IEEE Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit). The final published version will be available via IEEE Xplore

Journal ref 2026 IEEE Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit)