Uncertainty for SVBRDF Acquisition using Frequency Analysis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wiersma, Ruben, Philip, Julien, Hašan, Miloš, Mullia, Krishna, Luan, Fujun, Eisemann, Elmar, Deschaintre, Valentin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915275899666432
author Wiersma, Ruben
Philip, Julien
Hašan, Miloš
Mullia, Krishna
Luan, Fujun
Eisemann, Elmar
Deschaintre, Valentin
author_facet Wiersma, Ruben
Philip, Julien
Hašan, Miloš
Mullia, Krishna
Luan, Fujun
Eisemann, Elmar
Deschaintre, Valentin
contents This paper aims to quantify uncertainty for SVBRDF acquisition in multi-view captures. Under uncontrolled illumination and unstructured viewpoints, there is no guarantee that the observations contain enough information to reconstruct the appearance properties of a captured object. We study this ambiguity, or uncertainty, using entropy and accelerate the analysis by using the frequency domain, rather than the domain of incoming and outgoing viewing angles. The result is a method that computes a map of uncertainty over an entire object within a millisecond. We find that the frequency model allows us to recover SVBRDF parameters with competitive performance, that the accelerated entropy computation matches results with a physically-based path tracer, and that there is a positive correlation between error and uncertainty. We then show that the uncertainty map can be applied to improve SVBRDF acquisition using capture guidance, sharing information on the surface, and using a diffusion model to inpaint uncertain regions. Our code is available at https://github.com/rubenwiersma/svbrdf_uncertainty.
format Preprint
id arxiv_https___arxiv_org_abs_2406_17774
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Uncertainty for SVBRDF Acquisition using Frequency Analysis
Wiersma, Ruben
Philip, Julien
Hašan, Miloš
Mullia, Krishna
Luan, Fujun
Eisemann, Elmar
Deschaintre, Valentin
Computer Vision and Pattern Recognition
Graphics
This paper aims to quantify uncertainty for SVBRDF acquisition in multi-view captures. Under uncontrolled illumination and unstructured viewpoints, there is no guarantee that the observations contain enough information to reconstruct the appearance properties of a captured object. We study this ambiguity, or uncertainty, using entropy and accelerate the analysis by using the frequency domain, rather than the domain of incoming and outgoing viewing angles. The result is a method that computes a map of uncertainty over an entire object within a millisecond. We find that the frequency model allows us to recover SVBRDF parameters with competitive performance, that the accelerated entropy computation matches results with a physically-based path tracer, and that there is a positive correlation between error and uncertainty. We then show that the uncertainty map can be applied to improve SVBRDF acquisition using capture guidance, sharing information on the surface, and using a diffusion model to inpaint uncertain regions. Our code is available at https://github.com/rubenwiersma/svbrdf_uncertainty.
title Uncertainty for SVBRDF Acquisition using Frequency Analysis
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2406.17774