DDS combines DINOv2/SAM3 multi-level distillation with superpoint graph diffusion to produce label-free 3D semantic segmentation on driving LiDAR, beating several structure-oriented unsupervised baselines on nuScenes and SemanticKITTI.
Maskclus- tering: View consensus based mask graph clustering for open-vocabulary 3d instance segmentation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Distill, Diffuse, Segment: Unsupervised 3D Semantic Segmentation for Autonomous Driving Based on Multi-Level Distillation and Graph Diffusion
DDS combines DINOv2/SAM3 multi-level distillation with superpoint graph diffusion to produce label-free 3D semantic segmentation on driving LiDAR, beating several structure-oriented unsupervised baselines on nuScenes and SemanticKITTI.