Canny edges from an RGB image are projected into 3D, encoded with flipped TSDF, and fused with depth in a U-Net based CNN, improving semantic scene completion by about 3 points on SUNCG while matching complex two-stage methods on NYU.
Marr, Vision: A Computational Investigation into the Human Repre- sentation and Processing of Visual Information
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
-
EdgeNet: Semantic Scene Completion from a Single RGB-D Image
Canny edges from an RGB image are projected into 3D, encoded with flipped TSDF, and fused with depth in a U-Net based CNN, improving semantic scene completion by about 3 points on SUNCG while matching complex two-stage methods on NYU.