{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/texturegan-controlling-deep-image-synthesis","title":"TextureGAN: Controlling Deep Image Synthesis with Texture Patches","arxiv_id":"1706.02823","date":"2017-06-09","proceeding":"CVPR 2018 6","authors":["Wenqi Xian","Patsorn Sangkloy","Varun Agrawal","Amit Raj","Jingwan Lu","Chen Fang","Fisher Yu","James Hays"],"abstract":"In this paper, we investigate deep image synthesis guided by sketch, color,\nand texture. Previous image synthesis methods can be controlled by sketch and\ncolor strokes but we are the first to examine texture control. We allow a user\nto place a texture patch on a sketch at arbitrary locations and scales to\ncontrol the desired output texture. Our generative network learns to synthesize\nobjects consistent with these texture suggestions. To achieve this, we develop\na local texture loss in addition to adversarial and content loss to train the\ngenerative network. We conduct experiments using sketches generated from real\nimages and textures sampled from a separate texture database and results show\nthat our proposed algorithm is able to generate plausible images that are\nfaithful to user controls. Ablation studies show that our proposed pipeline can\ngenerate more realistic images than adapting existing methods directly.","url_abs":"http://arxiv.org/abs/1706.02823v3","url_pdf":"http://arxiv.org/pdf/1706.02823v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"texturegan-controlling-deep-image-synthesis","repo_url":"https://github.com/janesjanes/Pytorch-TextureGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"texturegan-controlling-deep-image-synthesis","repo_url":"https://github.com/kaziwasaleh/mask-guided","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"texturegan-controlling-deep-image-synthesis","repo_url":"https://github.com/yuchuanhui/TextureGanPython3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"texture-synthesis","task_name":"Texture Synthesis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-reconstruction-on-edge-to-handbags","task":"Image Reconstruction","dataset":"Edge-to-Handbags","model":"Xian et al._","rank_in_archive_order":2,"of":4,"metrics":{"FID":"60.848","LPIPS":"0.171"},"uses_additional_data":false},{"leaderboard":"/sota/image-reconstruction-on-edge-to-shoes","task":"Image Reconstruction","dataset":"Edge-to-Shoes","model":"Xian et al._","rank_in_archive_order":2,"of":4,"metrics":{"FID":"44.762","LPIPS":"0.124"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.02823","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}