On Demand Solid Texture Synthesis Using Deep 3D Networks
View/ Open
Date
2020Author
Gutierrez, J.
Rabin, J.
Galerne, B.
Hurtut, T.
Metadata
Show full item recordAbstract
This paper describes a novel approach for on demand volumetric texture synthesis based on a deep learning framework that allows for the generation of high‐quality three‐dimensional (3D) data at interactive rates. Based on a few example images of textures, a generative network is trained to synthesize coherent portions of solid textures of arbitrary sizes that reproduce the visual characteristics of the examples along some directions. To cope with memory limitations and computation complexity that are inherent to both high resolution and 3D processing on the GPU, only 2D textures referred to as ‘slices’ are generated during the training stage. These synthetic textures are compared to exemplar images a perceptual loss function based on a pre‐trained deep network. The proposed network is very light (less than 100k parameters), therefore it only requires sustainable training (i.e. few hours) and is capable of very fast generation (around a second for 256 voxels) on a single GPU. Integrated with a spatially seeded pseudo‐random number generator (PRNG) the proposed generator network directly returns a color value given a set of 3D coordinates. The synthesized volumes have good visual results that are at least equivalent to the state‐of‐the‐art patch‐based approaches. They are naturally seamlessly tileable and can be fully generated in parallel.
BibTeX
@article {10.1111:cgf.13889,
journal = {Computer Graphics Forum},
title = {{On Demand Solid Texture Synthesis Using Deep 3D Networks}},
author = {Gutierrez, J. and Rabin, J. and Galerne, B. and Hurtut, T.},
year = {2020},
publisher = {© 2020 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd},
ISSN = {1467-8659},
DOI = {10.1111/cgf.13889}
}
journal = {Computer Graphics Forum},
title = {{On Demand Solid Texture Synthesis Using Deep 3D Networks}},
author = {Gutierrez, J. and Rabin, J. and Galerne, B. and Hurtut, T.},
year = {2020},
publisher = {© 2020 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd},
ISSN = {1467-8659},
DOI = {10.1111/cgf.13889}
}
Collections
Related items
Showing items related by title, author, creator and subject.
-
Just-in-Time Texture Synthesis
Wang, Lili; Shi, Yulong; Chen, Yi; Popescu, Voicu (The Eurographics Association and Blackwell Publishing Ltd., 2013)Texture bombing is a texture synthesis approach that saves memory by stopping short of assembling the output texture from the arrangement of input texture patches; instead, the arrangement is used directly at run time to ... -
Mesh Color Textures
Yuksel, Cem (ACM, 2017)The fundamental limitations of texture mapping has been a long standing problem in computer graphics. The cost of defining and maintaining texture coordinates and the seams that introduce various filtering inconsistencies ... -
Texton Noise
Galerne, B.; Leclaire, A.; Moisan, L. (© 2017 The Eurographics Association and John Wiley & Sons Ltd., 2017)Designing realistic noise patterns from scratch is hard. To solve this problem, recent contributions have proposed involved spectral analysis algorithms that enable procedural noise models to faithfully reproduce some class ...