Show simple item record

dc.contributor.authorZhou, Xilongen_US
dc.contributor.authorHašan, Milošen_US
dc.contributor.authorDeschaintre, Valentinen_US
dc.contributor.authorGuerrero, Paulen_US
dc.contributor.authorSunkavalli, Kalyanen_US
dc.contributor.authorKalantari, Nima Khademien_US
dc.contributor.editorHauser, Helwig and Alliez, Pierreen_US
dc.date.accessioned2023-10-06T11:58:53Z
dc.date.available2023-10-06T11:58:53Z
dc.date.issued2023
dc.identifier.issn1467-8659
dc.identifier.urihttps://doi.org/10.1111/cgf.14781
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14781
dc.description.abstractLightweight material capture methods require a material prior, defining the subspace of plausible textures within the large space of unconstrained texel grids. Previous work has either used deep neural networks (trained on large synthetic material datasets) or procedural node graphs (constructed by expert artists) as such priors. In this paper, we propose a semi‐procedural differentiable material prior that represents materials as a set of (typically procedural) grayscale noises and patterns that are processed by a sequence of lightweight learnable convolutional filter operations. We demonstrate that the restricted structure of this architecture acts as an inductive bias on the space of material appearances, allowing us to optimize the weights of the convolutions per‐material, with no need for pre‐training on a large dataset. Combined with a differentiable rendering step and a perceptual loss, we enable single‐image tileable material capture comparable with state of the art. Our approach does not target the pixel‐perfect recovery of the material, but rather uses noises and patterns as input to match the target appearance. To achieve this, it does not require complex procedural graphs, and has a much lower complexity, computational cost and storage cost. We also enable control over the results, through changing the provided patterns and using guide maps to push the material properties towards a user‐driven objective.en_US
dc.publisher© 2023 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd.en_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectrendering
dc.titleA Semi‐Procedural Convolutional Material Prioren_US
dc.description.seriesinformationComputer Graphics Forum
dc.description.sectionheadersORIGINAL ARTICLES
dc.description.volume42
dc.description.number6
dc.identifier.doi10.1111/cgf.14781


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution 4.0 International License
Except where otherwise noted, this item's license is described as Attribution 4.0 International License