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.
%0 Generic
%1 kato2020differentiable
%A Kato, Hiroharu
%A Beker, Deniz
%A Morariu, Mihai
%A Ando, Takahiro
%A Matsuoka, Toru
%A Kehl, Wadim
%A Gaidon, Adrien
%D 2020
%K 2020 graphics rendering survey
%T Differentiable Rendering: A Survey
%U http://arxiv.org/abs/2006.12057
%X 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.
@misc{kato2020differentiable,
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.},
added-at = {2021-04-25T09:13:08.000+0200},
author = {Kato, Hiroharu and Beker, Deniz and Morariu, Mihai and Ando, Takahiro and Matsuoka, Toru and Kehl, Wadim and Gaidon, Adrien},
biburl = {https://www.bibsonomy.org/bibtex/2d1193290789aef37086e3fa699029553/analyst},
description = {[2006.12057] Differentiable Rendering: A Survey},
interhash = {b11da31f4bdfc5a2c43bff2af17cf0d3},
intrahash = {d1193290789aef37086e3fa699029553},
keywords = {2020 graphics rendering survey},
note = {cite arxiv:2006.12057},
timestamp = {2021-04-25T09:13:08.000+0200},
title = {Differentiable Rendering: A Survey},
url = {http://arxiv.org/abs/2006.12057},
year = 2020
}