{"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/internal-distribution-matching-for-natural","title":"InGAN: Capturing and Remapping the \"DNA\" of a Natural Image","arxiv_id":"1812.00231","date":"2018-12-01","proceeding":null,"authors":["Assaf Shocher","Shai Bagon","Phillip Isola","Michal Irani"],"abstract":"Generative Adversarial Networks (GANs) typically learn a distribution of\nimages in a large image dataset, and are then able to generate new images from\nthis distribution. However, each natural image has its own internal statistics,\ncaptured by its unique distribution of patches. In this paper we propose an\n\"Internal GAN\" (InGAN) - an image-specific GAN - which trains on a single input\nimage and learns its internal distribution of patches. It is then able to\nsynthesize a plethora of new natural images of significantly different sizes,\nshapes and aspect-ratios - all with the same internal patch-distribution (same\n\"DNA\") as the input image. In particular, despite large changes in global\nsize/shape of the image, all elements inside the image maintain their local\nsize/shape. InGAN is fully unsupervised, requiring no additional data other\nthan the input image itself. Once trained on the input image, it can remap the\ninput to any size or shape in a single feedforward pass, while preserving the\nsame internal patch distribution. InGAN provides a unified framework for a\nvariety of tasks, bridging the gap between textures and natural images.","url_abs":"http://arxiv.org/abs/1812.00231v2","url_pdf":"http://arxiv.org/pdf/1812.00231v2.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":"internal-distribution-matching-for-natural","repo_url":"https://github.com/assafshocher/InGAN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1812.00231","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}