{"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/disentangling-physical-dynamics-from-unknown","title":"Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Prediction","arxiv_id":"2003.01460","date":"2020-03-03","proceeding":"CVPR 2020 6","authors":["Vincent Le Guen","Nicolas Thome"],"abstract":"Leveraging physical knowledge described by partial differential equations (PDEs) is an appealing way to improve unsupervised video prediction methods. Since physics is too restrictive for describing the full visual content of generic videos, we introduce PhyDNet, a two-branch deep architecture, which explicitly disentangles PDE dynamics from unknown complementary information. A second contribution is to propose a new recurrent physical cell (PhyCell), inspired from data assimilation techniques, for performing PDE-constrained prediction in latent space. Extensive experiments conducted on four various datasets show the ability of PhyDNet to outperform state-of-the-art methods. Ablation studies also highlight the important gain brought out by both disentanglement and PDE-constrained prediction. Finally, we show that PhyDNet presents interesting features for dealing with missing data and long-term forecasting.","url_abs":"https://arxiv.org/abs/2003.01460v2","url_pdf":"https://arxiv.org/pdf/2003.01460v2.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":"disentangling-physical-dynamics-from-unknown","repo_url":"https://github.com/vincent-leguen/PhyDNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"disentangling-physical-dynamics-from-unknown","repo_url":"https://github.com/chengtan9907/simvpv2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"disentangling-physical-dynamics-from-unknown","repo_url":"https://github.com/cognitivemodeling/finn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"disentanglement","task_name":"Disentanglement"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"video-prediction","task_name":"Video Prediction"},{"task_slug":"weather-forecasting","task_name":"Weather Forecasting"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-prediction-on-human36m","task":"Video Prediction","dataset":"Human3.6M","model":"PhyDNet","rank_in_archive_order":5,"of":9,"metrics":{"MAE":"1620","MSE":"369","SSIM":"0.901"},"uses_additional_data":false},{"leaderboard":"/sota/video-prediction-on-moving-mnist","task":"Video Prediction","dataset":"Moving MNIST","model":"PhyDNet","rank_in_archive_order":19,"of":31,"metrics":{"MAE":"70.3","MSE":"24.4","SSIM":"0.947"},"uses_additional_data":false},{"leaderboard":"/sota/video-prediction-on-synpickvp","task":"Video Prediction","dataset":"SynpickVP","model":"PhyDNet","rank_in_archive_order":3,"of":5,"metrics":{"LPIPS":"0.053","MSE":"57.31","PSNR":"26.84","SSIM":"0.877"},"uses_additional_data":false},{"leaderboard":"/sota/weather-forecasting-on-sevir","task":"Weather Forecasting","dataset":"SEVIR","model":"PhyDNet","rank_in_archive_order":8,"of":8,"metrics":{"MSE":"4.8165","mCSI":"0.3940"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2003.01460","atlas_url":"https://app.syntology.ai/?focus=2003.01460","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.01460"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cognitivemodeling/finn","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chengtan9907/simvpv2","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vincent-leguen/PhyDNet","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"f64cea7e1e3eb13c","entry":"tensordot","repo":"vincent-leguen/PhyDNet","repo_kind":"official","path":"constrain_moments.py","file_url":"https://github.com/vincent-leguen/PhyDNet/blob/HEAD/constrain_moments.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f64cea7e1e3eb13c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}