GRCVMay 27, 2021

Passing Multi-Channel Material Textures to a 3-Channel Loss

arXiv:2105.13012v16 citations
Originality Incremental advance
AI Analysis

This addresses a limitation in neural textural losses for physically based rendering, though it appears incremental as it adapts existing loss frameworks.

The paper tackles the problem of training texture generators with multiple material channels by proposing a method to pass random triplets to a 3-channel loss, enabling high-quality multi-channel texture generation.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes