A point-based 3D segmentation network with back-projected 2D features and global context raises ScanNet test mIoU to 63.4%, up from 62.1% with original poses and from 48.4% for 3DMV.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Unified Point-Based Framework for 3D Segmentation
A point-based 3D segmentation network with back-projected 2D features and global context raises ScanNet test mIoU to 63.4%, up from 62.1% with original poses and from 48.4% for 3DMV.