VaViT adapts vanilla ViT for point cloud semantic segmentation on nuScenes, SemanticKITTI, and Waymo, matching or exceeding SOTA performance with a tokenizer, lightweight decoder, and augmentations.
KPRNet: Improving projection-based LiDAR semantic segmentation.arXiv:2007.12668,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Vanilla ViT for Automotive Point Cloud Semantic Segmentation
VaViT adapts vanilla ViT for point cloud semantic segmentation on nuScenes, SemanticKITTI, and Waymo, matching or exceeding SOTA performance with a tokenizer, lightweight decoder, and augmentations.