A 3D self-calibrated convolution module plus feature and semantic distillation lets a LiDAR network learn from 2D image teachers without 3D labels.
One thousand and one hours: Self-driving motion prediction dataset,
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
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Domain Adaptation-Based Crossmodal Knowledge Distillation for 3D Semantic Segmentation
A 3D self-calibrated convolution module plus feature and semantic distillation lets a LiDAR network learn from 2D image teachers without 3D labels.