{"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/differentiable-image-parameterizations","title":"Differentiable Image Parameterizations","arxiv_id":null,"date":"2018-07-25","proceeding":"Distill 2018 7","authors":["Alexander Mordvintsev","Nicola Pezzotti","Ludwig Schubert","Chris Olah"],"abstract":"Typically, we parameterize the input image as the RGB values of each pixel, but that isn’t the only way. As long as the mapping from parameters to images is differentiable, we can still optimize alternative parameterizations with gradient descent. \r\n\r\nDifferentiable image parameterizations invite us to ask “what kind of image generation process can we backpropagate through?” The answer is quite a lot, and some of the more exotic possibilities can create a wide range of interesting effects, including 3D neural art, images with transparency, and aligned interpolation. Previous work using specific unusual image parameterizations has shown exciting results — we think that zooming out and looking at this area as a whole suggests there’s even more potential.","url_abs":"https://distill.pub/2018/differentiable-parameterizations/","url_pdf":"https://distill.pub/2018/differentiable-parameterizations/","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":"differentiable-image-parameterizations","repo_url":"https://github.com/ProGamerGov/dream-creator","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"differentiable-image-parameterizations","repo_url":"https://github.com/tensorflow/lucid","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","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}