{"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/videoflow-a-flow-based-generative-model-for","title":"VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation","arxiv_id":"1903.01434","date":"2019-03-04","proceeding":"ICLR 2020 1","authors":["Manoj Kumar","Mohammad Babaeizadeh","Dumitru Erhan","Chelsea Finn","Sergey Levine","Laurent Dinh","Durk Kingma"],"abstract":"Generative models that can model and predict sequences of future events can, in principle, learn to capture complex real-world phenomena, such as physical interactions. However, a central challenge in video prediction is that the future is highly uncertain: a sequence of past observations of events can imply many possible futures. Although a number of recent works have studied probabilistic models that can represent uncertain futures, such models are either extremely expensive computationally as in the case of pixel-level autoregressive models, or do not directly optimize the likelihood of the data. To our knowledge, our work is the first to propose multi-frame video prediction with normalizing flows, which allows for direct optimization of the data likelihood, and produces high-quality stochastic predictions. We describe an approach for modeling the latent space dynamics, and demonstrate that flow-based generative models offer a viable and competitive approach to generative modelling of video.","url_abs":"https://arxiv.org/abs/1903.01434v3","url_pdf":"https://arxiv.org/pdf/1903.01434v3.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":"videoflow-a-flow-based-generative-model-for","repo_url":"https://github.com/tensorflow/tensor2tensor","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"predict-future-video-frames","task_name":"Predict Future Video Frames"},{"task_slug":"video-generation","task_name":"Video Generation"},{"task_slug":"video-prediction","task_name":"Video Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-generation-on-bair-robot-pushing","task":"Video Generation","dataset":"BAIR Robot Pushing","model":"VideoFlow","rank_in_archive_order":15,"of":31,"metrics":{"Cond":"3","FVD score":"131±5","Pred":"14 (total 16)","Train":"10"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.01434","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}