Our objective is to compute a textural loss that can be used to train texture generators with multiple material channels typically used for physically based rendering such as albedo, normal, roughness, metalness, ambient occlusion, etc. Neural textural losses often build on top of the feature spaces of pretrained convolutional neural networks. Unfortunately, these pretrained models are only available for 3-channel RGB data and hence limit neural textural losses to this format. To overcome this limitation, we show that passing random triplets to a 3-channel loss provides a multi-channel loss that can be used to generate high-quality material textures.
@article{arxiv.2105.13012,
title = {Passing Multi-Channel Material Textures to a 3-Channel Loss},
author = {Thomas Chambon and Eric Heitz and Laurent Belcour},
journal= {arXiv preprint arXiv:2105.13012},
year = {2021}
}