FocalFormer3D : Focusing on Hard Instance for 3D Object Detection
Yilun Chen, Zhiding Yu, Yukang Chen, Shiyi Lan, Animashree Anandkumar, Jiaya Jia, Jose Alvarez
- (2023/5/8) Our single multi-modal fusion model FocalFormer3D-F outshines all other non-TTA approaches on nuScenes Detection benchmark.
- (2023/3/10) FocalFormer3D ranks first on nuScenes LiDAR Detection benchmark.
- (2023/3/10) FocalFormer3D ranks first on nuScenes LiDAR Tracking benchmark.
- Release Code (Wait for the legal approval of NVIDIA.)