MixSup: Mixed-grained Supervision for Label-efficient LiDAR-based 3D Object Detection.

Yuxue Yang Lue Fan Zhaoxiang Zhang

Published in: CoRR (2024)

Keyphrases

d objects
multi view
object recognition
pose estimation
viewpoint
multiple views
detection method
three dimensional
active learning
lidar data
range data
real world objects
image contours
cad models
high resolution
object detection
shape descriptors
topological information
object views