1 code implementation • CVPR 2022 • Yi-Nan Chen, Hang Dai, Yong Ding
Motivated by this, we propose a Pseudo-Stereo 3D detection framework with three novel virtual view generation methods, including image-level generation, feature-level generation, and feature-clone, for detecting 3D objects from a single image.
Ranked #1 on Monocular 3D Object Detection on KITTI Cars Moderate (AP metric)