A weakly supervised 3D point cloud segmentation method that back-projects Semantic-SAM 2D masks into 3D, propagates sparse labels inside masks, and uses reliability-filtered pseudo labels, reporting state-of-the-art mIoU on ScanNetV2 and S3DIS.
Available: https://proceedings.neurips.cc/paper files/ paper/2018/hash/f5f8590cd58a54e94377e6ae2eded4d9-Abstract.html
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
-
Integrating SAM Supervision for 3D Weakly Supervised Point Cloud Segmentation
A weakly supervised 3D point cloud segmentation method that back-projects Semantic-SAM 2D masks into 3D, propagates sparse labels inside masks, and uses reliability-filtered pseudo labels, reporting state-of-the-art mIoU on ScanNetV2 and S3DIS.