“Passing Multi-Channel Material Textures to a 3-Channel Loss” by Chambon and Heitz
Conference:
Type(s):
Entry Number: 59
Title:
- Passing Multi-Channel Material Textures to a 3-Channel Loss
Presenter(s)/Author(s):
Abstract:
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.,
References:
Miika Aittala, Timo Aila, and Jaakko Lehtinen. 2016. Reflectance Modeling by Neural Texture Synthesis. ACM Trans. Graph. 35, 4, Article 65 (2016), 13 pages.
Leon A. Gatys, Alexander S. Ecker, and Matthias Bethge. 2015. Texture Synthesis Using Convolutional Neural Networks. In Proceedings of the 28th International Conference on Neural Information Processing Systems – Volume 1 (NIPS’15). 262–270.
Yijun Li, Chen Fang, Jimei Yang, Zhaowen Wang, Xin Lu, and Ming Hsuan Yang. 2017. Diversified texture synthesis with feed-forward networks. In Proceedings – 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. 266–274.
Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In International Conference on Learning Representations. Dmitry Ulyanov, Vadim Lebedev, Andrea Vedaldi, and Victor Lempitsky. 2016. Texture Networks: Feed-Forward Synthesis of Textures and Stylized Images. In Proceedings of the 33rd International Conference on International Conference on Machine Learning – Volume 48 (ICML’16). 1349–1357.
Additional Images:
