{"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/deep-bayesian-video-frame-interpolation","title":"Deep Bayesian Video Frame Interpolation","arxiv_id":null,"date":"2022-10-23","proceeding":"Conference 2022 10","authors":["ZHIYANG YU","Yu Zhang","Xujie Xiang","Dongqing Zou","Xijun Chen","Jimmy S. Ren"],"abstract":"Abstract. We present deep Bayesian video frame interpolation, a novel approach for upsampling a low frame-rate video temporally to its higher frame-rate counterpart. Our approach learns posterior distributions of optical flows and frames to be interpolated, which is optimized via learned gradient descent for fast convergence. Each learned step is a lightweight network manipulating gradients of the log-likelihood of estimated frames and flows. Such gradients, parameterized either explicitly or implicitly, model the fidelity of current estimations when matching real image and flow distributions to explain the input observations. With this approach we show new records on 8 of 10 benchmarks, using an architecture with half the parameters of the state-of-the-art model.","url_abs":"https://www.ecva.net/papers.php","url_pdf":"https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136750141.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":"deep-bayesian-video-frame-interpolation","repo_url":"https://github.com/Oceanlib/DBVI","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"video-frame-interpolation","task_name":"Video Frame Interpolation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-frame-interpolation-on-davis","task":"Video Frame Interpolation","dataset":"DAVIS","model":"DBVI","rank_in_archive_order":1,"of":2,"metrics":{"PSNR":"28.61","SSIM":"0.905"},"uses_additional_data":false},{"leaderboard":"/sota/video-frame-interpolation-on-gopro","task":"Video Frame Interpolation","dataset":"GoPro","model":"DBVI","rank_in_archive_order":1,"of":2,"metrics":{"PSNR":"31.73","SSIM":"0.947"},"uses_additional_data":false},{"leaderboard":"/sota/video-frame-interpolation-on-snu-film-easy","task":"Video Frame Interpolation","dataset":"SNU-FILM (easy)","model":"DBVI","rank_in_archive_order":3,"of":8,"metrics":{"PSNR":"40.46","SSIM":"0.991"},"uses_additional_data":false},{"leaderboard":"/sota/video-frame-interpolation-on-snu-film-extreme","task":"Video Frame Interpolation","dataset":"SNU-FILM (extreme)","model":"DBVI","rank_in_archive_order":1,"of":8,"metrics":{"PSNR":"25.90","SSIM":"0.876"},"uses_additional_data":false},{"leaderboard":"/sota/video-frame-interpolation-on-snu-film-hard","task":"Video Frame Interpolation","dataset":"SNU-FILM (hard)","model":"DBVI","rank_in_archive_order":2,"of":8,"metrics":{"PSNR":"31.68","SSIM":"0.953"},"uses_additional_data":false},{"leaderboard":"/sota/video-frame-interpolation-on-snu-film-medium","task":"Video Frame Interpolation","dataset":"SNU-FILM (medium)","model":"DBVI","rank_in_archive_order":2,"of":8,"metrics":{"PSNR":"36.95","SSIM":"0.985"},"uses_additional_data":false},{"leaderboard":"/sota/video-frame-interpolation-on-x4k1000fps","task":"Video Frame Interpolation","dataset":"X4K1000FPS","model":"DBVI","rank_in_archive_order":2,"of":20,"metrics":{"PSNR":"32.89","SSIM":"0.939"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}