A LiDAR-to-camera distillation method that supervises relative depth inside object foregrounds and distills BEV feature relationships to boost camera-only 3D object detection.
Mix-teaching: A simple, unified and effective semi-supervised learning framework for monocular 3d object detection,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
TiGDistill-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning Distillation
A LiDAR-to-camera distillation method that supervises relative depth inside object foregrounds and distills BEV feature relationships to boost camera-only 3D object detection.