The Challenges of Relighting from Multi-View Observations

Simple item page
dc.contributor.authorSiersleben, Danielen_US
dc.contributor.authorOrtiz-Cayon, Rodrigoen_US
dc.contributor.authorIstenic, Klemenen_US
dc.contributor.authorTomoto, Yusukeen_US
dc.contributor.authorSchaub-Meyer, Simoneen_US
dc.contributor.editorHardeberg, Jon Yngveen_US
dc.contributor.editorRushmeier, Hollyen_US
dc.date.accessioned2024-08-28T06:32:06Z
dc.date.available2024-08-28T06:32:06Z
dc.date.issued2024
dc.description.abstractHigh-quality geometry reconstruction from multi-view images with subsequent appearance decomposition into the physical shading components could enable a seamless integration of neural reconstructions into the modern rendering workflow. While 3D reconstruction techniques have steadily improved, the task of inverse rendering by decomposing an appearance into lighting effects and material properties remains fundamentally ill-posed and highly ambiguous. We show that current state-of-the-art inverse rendering approaches fail to accurately recover material properties, significantly impacting relighting quality. Furthermore, we demonstrate that existing evaluation methods, which rely on image-based metrics, do not adequately capture the reconstruction quality in novel lighting conditions. Our findings illustrate the dependence of current systems on simplified setups with predefined illumination, which are necessary to reliably disentangle light and material contributions and to ultimately achieve convincing relighting.en_US
dc.description.sectionheadersRepresentation / Capture / Wave Optics
dc.description.seriesinformationWorkshop on Material Appearance Modeling
dc.description.seriesinformationJoint MAM - MANER Conference - Material Appearance Network for Education and Research
dc.identifier.doi10.2312/mam.20241181
dc.identifier.isbn978-3-03868-264-6
dc.identifier.issn2309-5059
dc.identifier.pages4 pages
dc.identifier.urihttps://doi.org/10.2312/mam.20241181
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/mam20241181
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.titleThe Challenges of Relighting from Multi-View Observationsen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
mam20241181.pdf
Size:
9.53 MB
Format:
Adobe Portable Document Format
Download
Collections
MAM2024 - MANER Conference London 2024