GraphBEV: Towards Robust BEV Feature Alignment for Multi-Modal 3D Object Detection.
Ziying SongLei YangShaoqing XuLin LiuDongyang XuCaiyan JiaFeiyang JiaLi WangPublished in: CoRR (2024)
Keyphrases
- multi modal
- d objects
- pose normalization
- object features
- object recognition
- viewpoint
- pose estimation
- multiple views
- point distribution
- multi view
- multi modality
- partial occlusion
- cross modal
- range data
- shape descriptors
- d mesh
- object classes
- three dimensional
- image features
- physically plausible
- feature vectors
- image contours
- spin images
- cad models
- high dimensional
- uni modal
- spatial information
- object class
- feature set
- object detection
- integral imaging
- computer vision