SEFormer: Structure Embedding Transformer for 3D Object Detection.

Xiaoyu Feng Heming Du Hehe Fan Yueqi Duan Yongpan Liu

Published in: AAAI (2023)

Keyphrases

d objects
viewpoint
multi view
multiple views
range data
cad models
object recognition
three dimensional
pose estimation
object detection
shape descriptors
physically plausible
topological information
detection method
structural information
object model
image contours
d mesh
surface patches
object features