{"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/automatic-temporally-coherent-video","title":"Automatic Temporally Coherent Video Colorization","arxiv_id":"1904.09527","date":"2019-04-21","proceeding":null,"authors":["Harrish Thasarathan","Kamyar Nazeri","Mehran Ebrahimi"],"abstract":"Greyscale image colorization for applications in image restoration has seen\nsignificant improvements in recent years. Many of these techniques that use\nlearning-based methods struggle to effectively colorize sparse inputs. With the\nconsistent growth of the anime industry, the ability to colorize sparse input\nsuch as line art can reduce significant cost and redundant work for production\nstudios by eliminating the in-between frame colorization process. Simply using\nexisting methods yields inconsistent colors between related frames resulting in\na flicker effect in the final video. In order to successfully automate key\nareas of large-scale anime production, the colorization of line arts must be\ntemporally consistent between frames. This paper proposes a method to colorize\nline art frames in an adversarial setting, to create temporally coherent video\nof large anime by improving existing image to image translation methods. We\nshow that by adding an extra condition to the generator and discriminator, we\ncan effectively create temporally consistent video sequences from anime line\narts. Code and models available at: https://github.com/Harry-Thasarathan/TCVC","url_abs":"http://arxiv.org/abs/1904.09527v1","url_pdf":"http://arxiv.org/pdf/1904.09527v1.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":"automatic-temporally-coherent-video","repo_url":"https://github.com/Harry-Thasarathan/TCVC","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"automatic-temporally-coherent-video","repo_url":"https://github.com/iver56/automatic-video-colorization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"automatic-temporally-coherent-video","repo_url":"https://github.com/wwwAych/AutoVideoColor","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"colorization","task_name":"Colorization"},{"task_slug":"image-colorization","task_name":"Image Colorization"},{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"image-to-image-translation","task_name":"Image-to-Image Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"colorization","method_name":"Colorization"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1904.09527","atlas_url":"https://app.syntology.ai/?focus=1904.09527","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}