{"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/generative-face-completion","title":"Generative Face Completion","arxiv_id":"1704.05838","date":"2017-04-19","proceeding":"CVPR 2017 7","authors":["Yijun Li","Sifei Liu","Jimei Yang","Ming-Hsuan Yang"],"abstract":"In this paper, we propose an effective face completion algorithm using a deep\ngenerative model. Different from well-studied background completion, the face\ncompletion task is more challenging as it often requires to generate\nsemantically new pixels for the missing key components (e.g., eyes and mouths)\nthat contain large appearance variations. Unlike existing nonparametric\nalgorithms that search for patches to synthesize, our algorithm directly\ngenerates contents for missing regions based on a neural network. The model is\ntrained with a combination of a reconstruction loss, two adversarial losses and\na semantic parsing loss, which ensures pixel faithfulness and local-global\ncontents consistency. With extensive experimental results, we demonstrate\nqualitatively and quantitatively that our model is able to deal with a large\narea of missing pixels in arbitrary shapes and generate realistic face\ncompletion results.","url_abs":"http://arxiv.org/abs/1704.05838v1","url_pdf":"http://arxiv.org/pdf/1704.05838v1.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":"generative-face-completion","repo_url":"https://github.com/easternCar/Face-Parsing-Network","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"generative-face-completion","repo_url":"https://github.com/Yijunmaverick/GenerativeFaceCompletion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"torch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"facial-inpainting","task_name":"Facial Inpainting"},{"task_slug":"semantic-parsing","task_name":"Semantic Parsing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1704.05838","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}