loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Soroush Saryazdi ; Christian Murphy and Sudhir Mudur

Affiliation: Concordia University, Montréal, Canada

Keyword(s): Material Capture, Appearance Capture, SVBRDF, Deep Learning.

Abstract: In order to replicate the behavior of real world material using computer graphics, accurate material property maps must be predicted which are used in a pixel-wise multi-variable rendering function. Recent deep learning techniques use the rendered image to obtain the loss on the material property map predictions. While use of rendering loss defined this way results in some improvements in the quality of the predicted renderings, it has problems in recovering the individual property maps accurately. These inaccuracies arise due to the following: i) different property values can collectively generate the same image for limited light and view directions, ii) even correctly predicted property maps get changed because the loss backpropagates gradients to all, and iii) the heuristic chosen for number of light and view samples affects accuracy and computation time. We propose a new loss function, named disentangled rendering loss which addresses the above issues: each predicted property map is used with ground truth maps instead of the other predicted maps, and we solve for the integral of the L1 loss of the specular term over different light and view directions, thus avoiding the need for multiple light and view samples. We show that using our disentangled rendering loss to train the current state of the art network leads to a noticeable increase in the accuracy of recovered material property maps. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.136.22.204

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Saryazdi, S.; Murphy, C. and Mudur, S. (2021). Disentangled Rendering Loss for Supervised Material Property Recovery. In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - GRAPP; ISBN 978-989-758-488-6; ISSN 2184-4321, SciTePress, pages 113-121. DOI: 10.5220/0010330301130121

@conference{grapp21,
author={Soroush Saryazdi. and Christian Murphy. and Sudhir Mudur.},
title={Disentangled Rendering Loss for Supervised Material Property Recovery},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - GRAPP},
year={2021},
pages={113-121},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010330301130121},
isbn={978-989-758-488-6},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - GRAPP
TI - Disentangled Rendering Loss for Supervised Material Property Recovery
SN - 978-989-758-488-6
IS - 2184-4321
AU - Saryazdi, S.
AU - Murphy, C.
AU - Mudur, S.
PY - 2021
SP - 113
EP - 121
DO - 10.5220/0010330301130121
PB - SciTePress

- Science and Technology Publications, Lda.
RESOURCES

Proceedings

Papers

Authors

Ontology

CONTACTS

Science and Technology Publications, Lda
Avenida de S. Francisco Xavier, Lote 7 Cv. C,
2900-616 Setúbal, Portugal.

Phone: +351 265 520 185 (National fixed network call)
Fax: +351 265 520 186
Email: info@scitepress.org

EXTERNAL LINKS

PRIMORIS

INSTICC

SCITEVENTS

CROSSREF

PROCEEDINGS SUBMITTED FOR INDEXATION BY:

dblp

Ei Compendex

SCOPUS

Semantic Scholar

Google Scholar

Microsoft Academic