{"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/learning-texture-manifolds-with-the-periodic","title":"Learning Texture Manifolds with the Periodic Spatial GAN","arxiv_id":"1705.06566","date":"2017-05-18","proceeding":"ICML 2017 8","authors":["Urs Bergmann","Nikolay Jetchev","Roland Vollgraf"],"abstract":"This paper introduces a novel approach to texture synthesis based on\ngenerative adversarial networks (GAN) (Goodfellow et al., 2014). We extend the\nstructure of the input noise distribution by constructing tensors with\ndifferent types of dimensions. We call this technique Periodic Spatial GAN\n(PSGAN). The PSGAN has several novel abilities which surpass the current state\nof the art in texture synthesis. First, we can learn multiple textures from\ndatasets of one or more complex large images. Second, we show that the image\ngeneration with PSGANs has properties of a texture manifold: we can smoothly\ninterpolate between samples in the structured noise space and generate novel\nsamples, which lie perceptually between the textures of the original dataset.\nIn addition, we can also accurately learn periodical textures. We make multiple\nexperiments which show that PSGANs can flexibly handle diverse texture and\nimage data sources. Our method is highly scalable and it can generate output\nimages of arbitrary large size.","url_abs":"http://arxiv.org/abs/1705.06566v2","url_pdf":"http://arxiv.org/pdf/1705.06566v2.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":"learning-texture-manifolds-with-the-periodic","repo_url":"https://github.com/zalandoresearch/psgan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-texture-manifolds-with-the-periodic","repo_url":"https://github.com/Archangel212/psgan-batik","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-texture-manifolds-with-the-periodic","repo_url":"https://github.com/Archangel212/psgan-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-texture-manifolds-with-the-periodic","repo_url":"https://github.com/MQSchleich/SatelliteFAMOS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-texture-manifolds-with-the-periodic","repo_url":"https://github.com/a-maumau/psgan.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-texture-manifolds-with-the-periodic","repo_url":"https://github.com/oist/psgan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-texture-manifolds-with-the-periodic","repo_url":"https://github.com/zalandoresearch/famos","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"texture-synthesis","task_name":"Texture Synthesis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.06566","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}