MIPNet: Neural Normal-to-Anisotropic-Roughness MIP mapping - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue ACM Transactions on Graphics Année : 2022

MIPNet: Neural Normal-to-Anisotropic-Roughness MIP mapping

Résumé

We present MIPNet, a novel approach for SVBRDF mipmapping which preserves material appearance under varying view distances and lighting conditions. As in classical mipmapping, our method explicitly encodes the multiscale appearance of materials in a SVBRDF mipmap pyramid. To do so, we use a tensor-based representation, coping with gradient-based optimization, for encoding anisotropy which is compatible with existing real-time rendering engines. Instead of relying on a simple texture patch average for each channel independently, we propose a cascaded architecture of multilayer perceptrons to approximate the material appearance using only the fixed material channels. Our neural model learns simple mipmapping filters using a differentiable rendering pipeline based on a rendering loss and is able to transfer signal from normal to anisotropic roughness. As a result, we obtain a drop-in replacement for standard material mipmapping, offering a significant improvement in appearance preservation while still boiling down to a single per-pixel mipmap texture fetch. We report extensive experiments on two distinct BRDF models.
Fichier principal
Vignette du fichier
MIPNet.pdf (15.11 Mo) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-04001287 , version 1 (22-02-2023)

Identifiants

Citer

Alban Gauthier, Robin Faury, Jérémy Levallois, Théo Thonat, Jean-Marc Thiery, et al.. MIPNet: Neural Normal-to-Anisotropic-Roughness MIP mapping. ACM Transactions on Graphics, 2022, 41 (6), pp.1-12. ⟨10.1145/3550454.3555487⟩. ⟨hal-04001287⟩
139 Consultations
73 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More