A semi-supervised RGB-D scene parsing framework using patch swapping between RGB and depth, lightweight depth feature injection, and depth-derived boundary supervision reports state-of-the-art results on NYUv2 and first place on the KITTI Semantics benchmark.
Complementary random masking for rgb-thermal seman- tic segmentation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
DepthMatch: Semi-Supervised RGB-D Scene Parsing through Depth-Guided Regularization
A semi-supervised RGB-D scene parsing framework using patch swapping between RGB and depth, lightweight depth feature injection, and depth-derived boundary supervision reports state-of-the-art results on NYUv2 and first place on the KITTI Semantics benchmark.