{"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/neural-face-editing-with-intrinsic-image","title":"Neural Face Editing with Intrinsic Image Disentangling","arxiv_id":"1704.04131","date":"2017-04-13","proceeding":"CVPR 2017 7","authors":["Zhixin Shu","Ersin Yumer","Sunil Hadap","Kalyan Sunkavalli","Eli Shechtman","Dimitris Samaras"],"abstract":"Traditional face editing methods often require a number of sophisticated and\ntask specific algorithms to be applied one after the other --- a process that\nis tedious, fragile, and computationally intensive. In this paper, we propose\nan end-to-end generative adversarial network that infers a face-specific\ndisentangled representation of intrinsic face properties, including shape (i.e.\nnormals), albedo, and lighting, and an alpha matte. We show that this network\ncan be trained on \"in-the-wild\" images by incorporating an in-network\nphysically-based image formation module and appropriate loss functions. Our\ndisentangling latent representation allows for semantically relevant edits,\nwhere one aspect of facial appearance can be manipulated while keeping\northogonal properties fixed, and we demonstrate its use for a number of facial\nediting applications.","url_abs":"http://arxiv.org/abs/1704.04131v1","url_pdf":"http://arxiv.org/pdf/1704.04131v1.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":"neural-face-editing-with-intrinsic-image","repo_url":"https://github.com/zhixinshu/NeuralFaceEditing","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"neural-face-editing-with-intrinsic-image","repo_url":"https://github.com/kpahwa16/BioFacenet-Pytorch-Implementation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"facial-editing","task_name":"Facial Editing"},{"task_slug":null,"task_name":"Generative Adversarial Network"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1704.04131","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}