{"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-video-portrait-relighting-in-real-time","title":"Neural Video Portrait Relighting in Real-time via Consistency Modeling","arxiv_id":"2104.00484","date":"2021-04-01","proceeding":"ICCV 2021 10","authors":["Longwen Zhang","Qixuan Zhang","Minye Wu","Jingyi Yu","Lan Xu"],"abstract":"Video portraits relighting is critical in user-facing human photography, especially for immersive VR/AR experience. Recent advances still fail to recover consistent relit result under dynamic illuminations from monocular RGB stream, suffering from the lack of video consistency supervision. In this paper, we propose a neural approach for real-time, high-quality and coherent video portrait relighting, which jointly models the semantic, temporal and lighting consistency using a new dynamic OLAT dataset. We propose a hybrid structure and lighting disentanglement in an encoder-decoder architecture, which combines a multi-task and adversarial training strategy for semantic-aware consistency modeling. We adopt a temporal modeling scheme via flow-based supervision to encode the conjugated temporal consistency in a cross manner. We also propose a lighting sampling strategy to model the illumination consistency and mutation for natural portrait light manipulation in real-world. Extensive experiments demonstrate the effectiveness of our approach for consistent video portrait light-editing and relighting, even using mobile computing.","url_abs":"https://arxiv.org/abs/2104.00484v1","url_pdf":"https://arxiv.org/pdf/2104.00484v1.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-video-portrait-relighting-in-real-time","repo_url":"https://github.com/ZoneLikeWonderland/Neural-Video-Portrait-Relighting-in-Real-time-via-Consistency-Modeling","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"disentanglement","task_name":"Disentanglement"},{"task_slug":"single-image-portrait-relighting","task_name":"Single-Image Portrait Relighting"}],"methods":[],"datasets_introduced":[{"slug":"dynamic-olat-dataset","name":"Dynamic OLAT Dataset","full_name":"ShanghaiTech MARS Dynamic OLAT Dataset"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2104.00484","atlas_url":"https://app.syntology.ai/?focus=2104.00484","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}