{"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/sfsnet-learning-shape-reflectance-and-1","title":"SfSNet: Learning Shape, Reflectance and Illuminance of Faces in the Wild","arxiv_id":"1712.01261","date":"2017-12-02","proceeding":"CVPR 2018","authors":["Soumyadip Sengupta","Angjoo Kanazawa","Carlos D. Castillo","David Jacobs"],"abstract":"We present SfSNet, an end-to-end learning framework for producing an accurate\ndecomposition of an unconstrained human face image into shape, reflectance and\nilluminance. SfSNet is designed to reflect a physical lambertian rendering\nmodel. SfSNet learns from a mixture of labeled synthetic and unlabeled real\nworld images. This allows the network to capture low frequency variations from\nsynthetic and high frequency details from real images through the photometric\nreconstruction loss. SfSNet consists of a new decomposition architecture with\nresidual blocks that learns a complete separation of albedo and normal. This is\nused along with the original image to predict lighting. SfSNet produces\nsignificantly better quantitative and qualitative results than state-of-the-art\nmethods for inverse rendering and independent normal and illumination\nestimation.","url_abs":"http://arxiv.org/abs/1712.01261v2","url_pdf":"http://arxiv.org/pdf/1712.01261v2.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":"sfsnet-learning-shape-reflectance-and-1","repo_url":"https://github.com/senguptaumd/SfSNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"inverse-rendering","task_name":"Inverse Rendering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1712.01261","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}