A network that outputs the weights of a per-shape point classifier reconstructs 3D shapes from single images more accurately than voxel, point cloud, and mesh baselines.
Occupancy networks: Learning 3d reconstruction in function space, 2018
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
-
Deep Meta Functionals for Shape Representation
A network that outputs the weights of a per-shape point classifier reconstructs 3D shapes from single images more accurately than voxel, point cloud, and mesh baselines.