{"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/gans-for-biological-image-synthesis","title":"GANs for Biological Image Synthesis","arxiv_id":"1708.04692","date":"2017-08-15","proceeding":"ICCV 2017 10","authors":["Anton Osokin","Anatole Chessel","Rafael E. Carazo Salas","Federico Vaggi"],"abstract":"In this paper, we propose a novel application of Generative Adversarial\nNetworks (GAN) to the synthesis of cells imaged by fluorescence microscopy.\nCompared to natural images, cells tend to have a simpler and more geometric\nglobal structure that facilitates image generation. However, the correlation\nbetween the spatial pattern of different fluorescent proteins reflects\nimportant biological functions, and synthesized images have to capture these\nrelationships to be relevant for biological applications. We adapt GANs to the\ntask at hand and propose new models with casual dependencies between image\nchannels that can generate multi-channel images, which would be impossible to\nobtain experimentally. We evaluate our approach using two independent\ntechniques and compare it against sensible baselines. Finally, we demonstrate\nthat by interpolating across the latent space we can mimic the known changes in\nprotein localization that occur through time during the cell cycle, allowing us\nto predict temporal evolution from static images.","url_abs":"http://arxiv.org/abs/1708.04692v2","url_pdf":"http://arxiv.org/pdf/1708.04692v2.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":"gans-for-biological-image-synthesis","repo_url":"https://github.com/aosokin/biogans","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}