A graph-convolution network that iteratively deforms a coarse mesh using pooled multi-view image features produces more accurate 3D shapes from a few images than prior single- and multi-view methods on ShapeNet.
Bronstein, Joan Bruna, Yann LeCun, Arthur Szlam, and Pierre Vandergheynst
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
-
Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformation
A graph-convolution network that iteratively deforms a coarse mesh using pooled multi-view image features produces more accurate 3D shapes from a few images than prior single- and multi-view methods on ShapeNet.