Multi-View Supervision for Single-View Reconstruction via Differentiable Ray Consistency

Shubham Tulsiani, Tinghui Zhou, Alexei A. Efros, Jitendra Malik; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 2626-2634

Abstract


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.

Related Material


[pdf] [arXiv] [video]
[bibtex]
@InProceedings{Tulsiani_2017_CVPR,
author = {Tulsiani, Shubham and Zhou, Tinghui and Efros, Alexei A. and Malik, Jitendra},
title = {Multi-View Supervision for Single-View Reconstruction via Differentiable Ray Consistency},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {July},
year = {2017}
}