MesoGAN: Generative Neural Reflectance Shells

Simple item page
dc.contributor.authorDiolatzis, Stavrosen_US
dc.contributor.authorNovak, Janen_US
dc.contributor.authorRousselle, Fabriceen_US
dc.contributor.authorGranskog, Jonathanen_US
dc.contributor.authorAittala, Miikaen_US
dc.contributor.authorRamamoorthi, Ravien_US
dc.contributor.authorDrettakis, Georgeen_US
dc.contributor.editorHauser, Helwig and Alliez, Pierreen_US
dc.date.accessioned2023-10-06T11:58:51Z
dc.date.available2023-10-06T11:58:51Z
dc.date.issued2023
dc.description.abstractWe introduce MesoGAN, a model for generative 3D neural textures. This new graphics primitive represents mesoscale appearance by combining the strengths of generative adversarial networks (StyleGAN) and volumetric neural field rendering. The primitive can be applied to surfaces as a neural reflectance shell; a thin volumetric layer above the surface with appearance parameters defined by a neural network. To construct the neural shell, we first generate a 2D feature texture using StyleGAN with carefully randomized Fourier features to support arbitrarily sized textures without repeating artefacts. We augment the 2D feature texture with a learned height feature, which aids the neural field renderer in producing volumetric parameters from the 2D texture. To facilitate filtering, and to enable end‐to‐end training within memory constraints of current hardware, we utilize a hierarchical texturing approach and train our model on multi‐scale synthetic datasets of 3D mesoscale structures. We propose one possible approach for conditioning MesoGAN on artistic parameters (e.g. fibre length, density of strands, lighting direction) and demonstrate and discuss integration into physically based renderers.en_US
dc.description.number6
dc.description.sectionheadersORIGINAL ARTICLES
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume42
dc.identifier.doi10.1111/cgf.14846
dc.identifier.issn1467-8659
dc.identifier.urihttps://doi.org/10.1111/cgf.14846
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14846
dc.publisher© 2023 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd.en_US
dc.subjectrendering
dc.subjectray tracing
dc.subjectrendering
dc.subjectglobal illumination
dc.subjectrendering
dc.subjectreflectance and shading models
dc.titleMesoGAN: Generative Neural Reflectance Shellsen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
v42i6_16_14846.pdf
Size:
14.79 MB
Format:
Adobe Portable Document Format
Download
Collections
42-Issue 6