TextureGAN: Controlling Deep Image Synthesis with Texture Patches

被引:178
作者
Xian, Wenqi [1 ]
Sangkloy, Patsorn [1 ]
Agrawal, Varun [1 ]
Raj, Amit [1 ]
Lu, Jingwan [2 ]
Fang, Chen [2 ]
Yu, Fisher [3 ]
Hays, James [1 ,4 ]
机构
[1] Georgia Inst Technol, Atlanta, GA 30332 USA
[2] Adobe Res, San Jose, CA USA
[3] Univ Calif Berkeley, Berkeley, CA USA
[4] Argo AI, Pittsburgh, PA USA
来源
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2018年
基金
美国国家科学基金会;
关键词
D O I
10.1109/CVPR.2018.00882
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, we investigate deep image synthesis guided by sketch, color, and texture. Previous image synthesis methods can be controlled by sketch and color strokes but we are the first to examine texture control. We allow a user to place a texture patch on a sketch at arbitrary locations and scales to control the desired output texture. Our generative network learns to synthesize objects consistent with these texture suggestions. To achieve this, we develop a local texture loss in addition to adversarial and content loss to train the generative network. We conduct experiments using sketches generated from real images and textures sampled from a separate texture database and results show that our proposed algorithm is able to generate plausible images that are faithful to user controls. Ablation studies show that our proposed pipeline can generate more realistic images than adapting existing methods directly.
引用
收藏
页码:8456 / 8465
页数:10
相关论文
共 49 条
[1]  
[Anonymous], 2016, ARXIV PREPRINT ARXIV
[2]  
[Anonymous], ARXIV161107865
[3]   PatchMatch: A Randomized Correspondence Algorithm for Structural Image Editing [J].
Barnes, Connelly ;
Shechtman, Eli ;
Finkelstein, Adam ;
Goldman, Dan B. .
ACM TRANSACTIONS ON GRAPHICS, 2009, 28 (03)
[4]  
Bergmann U., 2017, ARXIV PREPRINT ARXIV
[5]  
Chen TC, 2009, PROC EUR SOLID-STATE, P1
[6]  
Dosovitskiy A., 2014, CORR ABS 1411 5928
[7]  
Efros A. A., 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision, P1033, DOI 10.1109/ICCV.1999.790383
[8]  
Efros AA, 2001, COMP GRAPH, P341, DOI 10.1145/383259.383296
[9]   Textureshop: Texture synthesis as a photograph editing tool [J].
Fang, H ;
Hart, JC .
ACM TRANSACTIONS ON GRAPHICS, 2004, 23 (03) :354-359
[10]  
Gatys L., 2015, Texture Synthesis Using Convolutional Neural NetworksOpen Source Implementation on GitHub, P262