We study the notion of consistency between a 3D shape and a 2D observation and propose a differentiable formulation which allows computing gradients of the 3D shape given an observation from an arbitrary view. We do so by reformulating view consistency using a differentiable ray consistency (DRC) term. We show that this formulation can be incorporated in a learning framework to leverage different types of multi-view observations e.g. foreground masks, depth, color images, semantics etc. as supervision for learning single-view 3D prediction. We present empirical analysis of our technique in a controlled setting. We also show that this approach allows us to improve over existing techniques for single-view reconstruction of objects from the PASCAL VOC dataset.
@article{arxiv.1704.06254,
title = {Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistency},
author = {Shubham Tulsiani and Tinghui Zhou and Alexei A. Efros and Jitendra Malik},
journal= {arXiv preprint arXiv:1704.06254},
year = {2017}
}
Comments
To appear at CVPR 2017. Project webpage : https://shubhtuls.github.io/drc/