MatUp: Repurposing Image Upsamplers for SVBRDFs

Simple item page
dc.contributor.authorGauthier, Albanen_US
dc.contributor.authorKerbl, Bernharden_US
dc.contributor.authorLevallois, Jérémyen_US
dc.contributor.authorFaury, Robinen_US
dc.contributor.authorThiery, Jean-Marcen_US
dc.contributor.authorBoubekeur, Tamyen_US
dc.contributor.editorGarces, Elenaen_US
dc.contributor.editorHaines, Ericen_US
dc.date.accessioned2024-06-25T10:19:53Z
dc.date.available2024-06-25T10:19:53Z
dc.date.issued2024
dc.description.abstractWe propose MATUP, an upsampling filter for material super-resolution. Our method takes as input a low-resolution SVBRDF and upscales its maps so that their rendering under various lighting conditions fits upsampled renderings inferred in the radiance domain with pre-trained RGB upsamplers. We formulate our local filter as a compact Multilayer Perceptron (MLP), which acts on a small window of the input SVBRDF and is optimized using a data-fitting loss defined over upsampled radiance at various locations. This optimization is entirely performed at the scale of a single, independent material. Doing so, MATUP leverages the reconstruction capabilities acquired over large collections of natural images by pre-trained RGB models and provides regularization over self-similar structures. In particular, our light-weight neural filter avoids retraining complex architectures from scratch or accessing any large collection of low/high resolution material pairs - which do not actually exist at the scale RGB upsamplers are trained with. As a result, MATUP provides fine and coherent details in the upscaled material maps, as shown in the extensive evaluation we provide.en_US
dc.description.number4
dc.description.sectionheadersLight and Textures
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume43
dc.identifier.doi10.1111/cgf.15151
dc.identifier.issn1467-8659
dc.identifier.pages11 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.15151
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf15151
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Computing methodologies → Reflectance modeling; Texturing
dc.subjectComputing methodologies → Reflectance modeling
dc.subjectTexturing
dc.titleMatUp: Repurposing Image Upsamplers for SVBRDFsen_US
Files
Original bundle
Now showing 1 - 3 of 3
No Thumbnail Available
Name:
v43i4_07_cgf15151.pdf
Size:
63.34 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
paper1010.mp4
Size:
300.29 MB
Format:
Video MP4
Download
No Thumbnail Available
Name:
paper1010_supp.pdf
Size:
211.83 MB
Format:
Adobe Portable Document Format
Download
Collections
43-Issue 4