{"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/generative-networks-as-inverse-problems-with","title":"Generative networks as inverse problems with Scattering transforms","arxiv_id":"1805.06621","date":"2018-05-17","proceeding":"ICLR 2018 1","authors":["Tomás Angles","Stéphane Mallat"],"abstract":"Generative Adversarial Nets (GANs) and Variational Auto-Encoders (VAEs)\nprovide impressive image generations from Gaussian white noise, but the\nunderlying mathematics are not well understood. We compute deep convolutional\nnetwork generators by inverting a fixed embedding operator. Therefore, they do\nnot require to be optimized with a discriminator or an encoder. The embedding\nis Lipschitz continuous to deformations so that generators transform linear\ninterpolations between input white noise vectors into deformations between\noutput images. This embedding is computed with a wavelet Scattering transform.\nNumerical experiments demonstrate that the resulting Scattering generators have\nsimilar properties as GANs or VAEs, without learning a discriminative network\nor an encoder.","url_abs":"http://arxiv.org/abs/1805.06621v1","url_pdf":"http://arxiv.org/pdf/1805.06621v1.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":"generative-networks-as-inverse-problems-with","repo_url":"https://github.com/tomas-angles/generative-scattering-networks","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.06621","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}