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

Shubham Tulsiani, Tinghui Zhou, Alexei A. Efros, Jitendra Malik

CVPR 2017

doi:10.1109/CVPR.2017.30 /cvpr/2017/tulsiani2017cvpr-multiview/

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.

PDF CVPR Semantic Scholar

Cite

Text

Tulsiani et al. "Multi-View Supervision for Single-View Reconstruction via Differentiable Ray Consistency." Conference on Computer Vision and Pattern Recognition, 2017. doi:10.1109/CVPR.2017.30

Markdown

[Tulsiani et al. "Multi-View Supervision for Single-View Reconstruction via Differentiable Ray Consistency." Conference on Computer Vision and Pattern Recognition, 2017.](https://mlanthology.org/cvpr/2017/tulsiani2017cvpr-multiview/) doi:10.1109/CVPR.2017.30

BibTeX

@inproceedings{tulsiani2017cvpr-multiview,
  title     = {{Multi-View Supervision for Single-View Reconstruction via Differentiable Ray Consistency}},
  author    = {Tulsiani, Shubham and Zhou, Tinghui and Efros, Alexei A. and Malik, Jitendra},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2017},
  doi       = {10.1109/CVPR.2017.30},
  url       = {https://mlanthology.org/cvpr/2017/tulsiani2017cvpr-multiview/}
}