A pipeline segments aligned LiDAR point clouds by rendering intensity-colored 2D views, applying a camera-domain 2D segmentation model, and voting back-projected labels, producing competitive pseudo-labels for unsupervised domain adaptation.
Seg- ment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labels
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
-
3D Can Be Explored In 2D: Pseudo-Label Generation for LiDAR Point Clouds Using Sensor-Intensity-Based 2D Semantic Segmentation
A pipeline segments aligned LiDAR point clouds by rendering intensity-colored 2D views, applying a camera-domain 2D segmentation model, and voting back-projected labels, producing competitive pseudo-labels for unsupervised domain adaptation.