BriefGPT.xyz
Aug, 2023
GPA-3D: 无监督域自适应点云三维物体检测中的几何感知原型对齐
GPA-3D: Geometry-aware Prototype Alignment for Unsupervised Domain Adaptive 3D Object Detection from Point Clouds
HTML
PDF
Ziyu Li, Jingming Guo, Tongtong Cao, Liu Bingbing, Wankou Yang
TL;DR
提出了一种新颖的无监督领域自适应三维检测框架GPA-3D,通过显式利用点云对象的内在几何关系来减少特征差异,从而实现跨领域的转移,并在各种基准测试中证明了其优越性。
Abstract
lidar-based 3d detection
has made great progress in recent years. However, the performance of 3D detectors is considerably limited when deployed in unseen environments, owing to the severe domain gap problem. Existing
d
→