Estimating Uncertainty in Appearance Acquisition

Simple item page
dc.contributor.authorZhou, Zhiqianen_US
dc.contributor.authorZhang, Chengen_US
dc.contributor.authorDong, Zhaoen_US
dc.contributor.authorMarshall, Carlen_US
dc.contributor.authorZhao, Shuangen_US
dc.contributor.editorHaines, Ericen_US
dc.contributor.editorGarces, Elenaen_US
dc.date.accessioned2024-06-25T11:05:37Z
dc.date.available2024-06-25T11:05:37Z
dc.date.issued2024
dc.description.abstractThe inference of material reflectance from physical observations (e.g., photographs) is usually under-constrained, causing point estimates to suffer from ambiguity and, thus, generalize poorly to novel configurations. Conventional methods address this problem by using dense observations or introducing priors. In this paper, we tackle this problem from a different angle by introducing a method to quantify uncertainties. Based on a Bayesian formulation, our method can quantitatively analyze how under-constrained a material inference problem is (given the observations and priors), by sampling the entire posterior distribution of material parameters rather than optimizing a single point estimate as given by most inverse rendering methods. Further, we present a method to guide acquisition processes by recommending viewing/lighting configurations for making additional observations. We demonstrate the usefulness of our technique using several synthetic and one real example.en_US
dc.description.sectionheadersRelighting
dc.description.seriesinformationEurographics Symposium on Rendering
dc.identifier.doi10.2312/sr.20241149
dc.identifier.isbn978-3-03868-262-2
dc.identifier.issn1727-3463
dc.identifier.pages11 pages
dc.identifier.urihttps://doi.org/10.2312/sr.20241149
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/sr20241149
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subject!-
dc.subject!
dc.titleEstimating Uncertainty in Appearance Acquisitionen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
04_sr20241149.pdf
Size:
29.26 MB
Format:
Adobe Portable Document Format
Download
Collections
Rendering 2024 - Symposium Track