Adrien Gaidon

Adrien Gaidon

Director of Machine Learning at TRI (Toyota Research Institute) and Adjunct Professor at Stanford.

Differentiable Rendering: A Survey

H. Kato, D. Beker, M. Morariu, T. Ando, T. Matsuoka, W. Kehl, A. Gaidon

Published in arXiv - June 2020

Links: arxiv, bibtex

Differentiable rendering overview

Abstract

Deep neural networks (DNNs) have shown remarkable performance improvements on vision-related tasks such as object detection or image segmentation. Despite their success, they generally lack the understanding of 3D objects which form the image, as it is not always possible to collect 3D information about the scene or to easily annotate it. Differentiable rendering is a novel field which allows the gradients of 3D objects to be calculated and propagated through images. It also reduces the requirement of 3D data collection and annotation, while enabling higher success rate in various applications. This paper reviews existing literature and discusses the current state of differentiable rendering, its applications and open research problems.

Differentiable rendering training overview

Differentiable rendering libraries overview

Bibtex

@article{kato2020differentiable,
    title={Differentiable Rendering: A Survey},
    author={Hiroharu Kato and Deniz Beker and Mihai Morariu and Takahiro Ando
        and Toru Matsuoka and Wadim Kehl and Adrien Gaidon},
    year={2020},
    journal={arXiv preprint arXiv:2006.12057},
}