Non-Stationary Texture Synthesis by Adversarial Expansion
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2018
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909061699600384 |
|---|---|
| author | Zhou, Yang Zhu, Zhen Bai, Xiang Lischinski, Dani Cohen-Or, Daniel Huang, Hui |
| author_facet | Zhou, Yang Zhu, Zhen Bai, Xiang Lischinski, Dani Cohen-Or, Daniel Huang, Hui |
| contents | The real world exhibits an abundance of non-stationary textures. Examples include textures with large-scale structures, as well as spatially variant and inhomogeneous textures. While existing example-based texture synthesis methods can cope well with stationary textures, non-stationary textures still pose a considerable challenge, which remains unresolved. In this paper, we propose a new approach for example-based non-stationary texture synthesis. Our approach uses a generative adversarial network (GAN), trained to double the spatial extent of texture blocks extracted from a specific texture exemplar. Once trained, the fully convolutional generator is able to expand the size of the entire exemplar, as well as of any of its sub-blocks. We demonstrate that this conceptually simple approach is highly effective for capturing large-scale structures, as well as other non-stationary attributes of the input exemplar. As a result, it can cope with challenging textures, which, to our knowledge, no other existing method can handle. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_1805_04487 |
| institution | arXiv |
| publishDate | 2018 |
| record_format | arxiv |
| spellingShingle | Non-Stationary Texture Synthesis by Adversarial Expansion Zhou, Yang Zhu, Zhen Bai, Xiang Lischinski, Dani Cohen-Or, Daniel Huang, Hui Graphics Computer Vision and Pattern Recognition The real world exhibits an abundance of non-stationary textures. Examples include textures with large-scale structures, as well as spatially variant and inhomogeneous textures. While existing example-based texture synthesis methods can cope well with stationary textures, non-stationary textures still pose a considerable challenge, which remains unresolved. In this paper, we propose a new approach for example-based non-stationary texture synthesis. Our approach uses a generative adversarial network (GAN), trained to double the spatial extent of texture blocks extracted from a specific texture exemplar. Once trained, the fully convolutional generator is able to expand the size of the entire exemplar, as well as of any of its sub-blocks. We demonstrate that this conceptually simple approach is highly effective for capturing large-scale structures, as well as other non-stationary attributes of the input exemplar. As a result, it can cope with challenging textures, which, to our knowledge, no other existing method can handle. |
| title | Non-Stationary Texture Synthesis by Adversarial Expansion |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/1805.04487 |