{"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/forging-new-worlds-high-resolution-synthetic","title":"Forging new worlds: high-resolution synthetic galaxies with chained generative adversarial networks","arxiv_id":"1811.03081","date":"2018-11-07","proceeding":null,"authors":["Levi Fussell","Ben Moews"],"abstract":"Astronomy of the 21st century increasingly finds itself with extreme\nquantities of data. This growth in data is ripe for modern technologies such as\ndeep image processing, which has the potential to allow astronomers to\nautomatically identify, classify, segment and deblend various astronomical\nobjects. In this paper, we explore the use of chained generative adversarial\nnetworks (GANs), a class of generative models that learn mappings from latent\nspaces to data distributions by modelling the joint distribution of the data,\nto produce physically realistic galaxy images as one use case of such models.\nIn cosmology, such datasets can aid in the calibration of shape measurements\nfor weak lensing by augmenting data with synthetic images. By measuring the\ndistributions of multiple physical properties, we show that images generated\nwith our approach closely follow the distributions of real galaxies, further\nestablishing state-of-the-art GAN architectures as a valuable tool for\nmodern-day astronomy.","url_abs":"http://arxiv.org/abs/1811.03081v3","url_pdf":"http://arxiv.org/pdf/1811.03081v3.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":"forging-new-worlds-high-resolution-synthetic","repo_url":"https://github.com/levifussell/forging_new_worlds","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"astronomy","task_name":"Astronomy"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.03081","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}