A probabilistic latent-variable framework for single-image 3D reconstruction achieves state-of-the-art IoU and EMD on ShapeNet while using 32^3 voxel outputs.
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
-
Probabilistic Reconstruction Networks for 3D Shape Inference from a Single Image
A probabilistic latent-variable framework for single-image 3D reconstruction achieves state-of-the-art IoU and EMD on ShapeNet while using 32^3 voxel outputs.