A cascaded context pyramid network with guided residual refinement achieves state-of-the-art full-resolution 3D semantic scene completion from a single depth map on SUNCG and NYU datasets.
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
-
Cascaded Context Pyramid for Full-Resolution 3D Semantic Scene Completion
A cascaded context pyramid network with guided residual refinement achieves state-of-the-art full-resolution 3D semantic scene completion from a single depth map on SUNCG and NYU datasets.