{"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/distilling-style-from-image-pairs-for-global","title":"Distilling Style from Image Pairs for Global Forward and Inverse Tone Mapping","arxiv_id":"2209.15165","date":"2022-09-30","proceeding":null,"authors":["Aamir Mustafa","Param Hanji","Rafal K. Mantiuk"],"abstract":"Many image enhancement or editing operations, such as forward and inverse tone mapping or color grading, do not have a unique solution, but instead a range of solutions, each representing a different style. Despite this, existing learning-based methods attempt to learn a unique mapping, disregarding this style. In this work, we show that information about the style can be distilled from collections of image pairs and encoded into a 2- or 3-dimensional vector. This gives us not only an efficient representation but also an interpretable latent space for editing the image style. We represent the global color mapping between a pair of images as a custom normalizing flow, conditioned on a polynomial basis of the pixel color. We show that such a network is more effective than PCA or VAE at encoding image style in low-dimensional space and lets us obtain an accuracy close to 40 dB, which is about 7-10 dB improvement over the state-of-the-art methods.","url_abs":"https://arxiv.org/abs/2209.15165v2","url_pdf":"https://arxiv.org/pdf/2209.15165v2.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":"distilling-style-from-image-pairs-for-global","repo_url":"https://github.com/aamir-mustafa/distil_style","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-enhancement","task_name":"Image Enhancement"},{"task_slug":"inverse-tone-mapping-1","task_name":"Inverse-Tone-Mapping"},{"task_slug":"tone-mapping","task_name":"Tone Mapping"},{"task_slug":"inverse-tone-mapping","task_name":"inverse tone mapping"}],"methods":[{"method_slug":"pca","method_name":"PCA"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2209.15165","atlas_url":"https://app.syntology.ai/?focus=2209.15165","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}