{"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/learning-selfie-friendly-abstraction-from","title":"Learning Selfie-Friendly Abstraction from Artistic Style Images","arxiv_id":"1805.02085","date":"2018-05-05","proceeding":null,"authors":["Yicun Liu","Jimmy Ren","Jianbo Liu","Jiawei Zhang","Xiaohao Chen"],"abstract":"Artistic style transfer can be thought as a process to generate different\nversions of abstraction of the original image. However, most of the artistic\nstyle transfer operators are not optimized for human faces thus mainly suffers\nfrom two undesirable features when applying them to selfies. First, the edges\nof human faces may unpleasantly deviate from the ones in the original image.\nSecond, the skin color is far from faithful to the original one which is\nusually problematic in producing quality selfies. In this paper, we take a\ndifferent approach and formulate this abstraction process as a gradient domain\nlearning problem. We aim to learn a type of abstraction which not only achieves\nthe specified artistic style but also circumvents the two aforementioned\ndrawbacks thus highly applicable to selfie photography. We also show that our\nmethod can be directly generalized to videos with high inter-frame consistency.\nOur method is also robust to non-selfie images, and the generalization to\nvarious kinds of real-life scenes is discussed. We will make our code publicly\navailable.","url_abs":"http://arxiv.org/abs/1805.02085v2","url_pdf":"http://arxiv.org/pdf/1805.02085v2.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":"learning-selfie-friendly-abstraction-from","repo_url":"https://github.com/DandilionLau/Selfie-Friendly-Abstraction","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"style-transfer","task_name":"Style Transfer"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}