BEV-LGKD: A Unified LiDAR-Guided Knowledge Distillation Framework for Multi-View BEV 3D Object Detection.
Jianing LiMing LuJiaming LiuYandong GuoYuan DuLi DuShanghang ZhangPublished in: IEEE Trans. Intell. Veh. (2024)
Keyphrases
- multi view
- d objects
- multiple views
- single view
- multi view learning
- depth map
- three dimensional
- photometric stereo
- camera calibration
- range images
- viewpoint
- semi supervised
- object recognition
- bundle adjustment
- multi views
- pose estimation
- surface reconstruction
- object detection
- d scene
- camera parameters
- view synthesis
- computer vision