{"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/the-visual-centrifuge-model-free-layered","title":"The Visual Centrifuge: Model-Free Layered Video Representations","arxiv_id":"1812.01461","date":"2018-12-04","proceeding":"CVPR 2019 6","authors":["Jean-Baptiste Alayrac","João Carreira","Andrew Zisserman"],"abstract":"True video understanding requires making sense of non-lambertian scenes where\nthe color of light arriving at the camera sensor encodes information about not\njust the last object it collided with, but about multiple mediums -- colored\nwindows, dirty mirrors, smoke or rain. Layered video representations have the\npotential of accurately modelling realistic scenes but have so far required\nstringent assumptions on motion, lighting and shape. Here we propose a\nlearning-based approach for multi-layered video representation: we introduce\nnovel uncertainty-capturing 3D convolutional architectures and train them to\nseparate blended videos. We show that these models then generalize to single\nvideos, where they exhibit interesting abilities: color constancy, factoring\nout shadows and separating reflections. We present quantitative and qualitative\nresults on real world videos.","url_abs":"http://arxiv.org/abs/1812.01461v2","url_pdf":"http://arxiv.org/pdf/1812.01461v2.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":"the-visual-centrifuge-model-free-layered","repo_url":"https://github.com/albert100121/MLVR-Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"color-constancy","task_name":"Color Constancy"},{"task_slug":"video-understanding","task_name":"Video Understanding"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1812.01461","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}