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

arXiv: https://arxiv.org/abs/2105.13012 · HTML: https://mlsanity.com/paper/2105.13012/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 5 references that are in the map.
- First posted on arXiv 27 May 2021.

## Builds on (most cited first, 3 of 3)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Texture Networks: Feed-forward Synthesis of Textures and Stylized Images](https://mlsanity.com/paper/1603.03417/) (2016)
- [Diversified Texture Synthesis with Feed-forward Networks](https://mlsanity.com/paper/1703.01664/) (2017)

## Built on by (most cited first, 6 of 6)

- [Random-Access Neural Compression of Material Textures](https://mlsanity.com/paper/2305.17105/) (2023)
- [Collaborative Control for Geometry-Conditioned PBR Image Generation](https://mlsanity.com/paper/2402.05919/) (2024)
- [UMat: Uncertainty-Aware Single Image High Resolution Material Capture](https://mlsanity.com/paper/2305.16312/) (2023)
- [SViM3D: Stable Video Material Diffusion for Single Image 3D Generation](https://mlsanity.com/paper/2510.08271/) (2025)
- [Jointly Generating Multi-view Consistent PBR Textures using Collaborative Control](https://mlsanity.com/paper/2410.06985/) (2024)
- [Neural Texture Compression using Hypernetworks](https://mlsanity.com/paper/2606.26913/) (2026)

## Abstract (arXiv)

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.