A 2.78M-parameter student distilled from a 46.16M-parameter Point Transformer V3 teacher stays within a few mIoU points on LiDAR segmentation while being roughly 16x smaller and 1.6x faster.
Semantickitti: A dataset for semantic scene understanding of lidar sequences
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Topology-Guided Knowledge Distillation for Efficient Point Cloud Processing
A 2.78M-parameter student distilled from a 46.16M-parameter Point Transformer V3 teacher stays within a few mIoU points on LiDAR segmentation while being roughly 16x smaller and 1.6x faster.