{"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-multi-scale-video-prediction-beyond-mean","title":"Deep multi-scale video prediction beyond mean square error","arxiv_id":"1511.05440","date":"2015-11-17","proceeding":null,"authors":["Michael Mathieu","Camille Couprie","Yann Lecun"],"abstract":"Learning to predict future images from a video sequence involves the\nconstruction of an internal representation that models the image evolution\naccurately, and therefore, to some degree, its content and dynamics. This is\nwhy pixel-space video prediction may be viewed as a promising avenue for\nunsupervised feature learning. In addition, while optical flow has been a very\nstudied problem in computer vision for a long time, future frame prediction is\nrarely approached. Still, many vision applications could benefit from the\nknowledge of the next frames of videos, that does not require the complexity of\ntracking every pixel trajectories. In this work, we train a convolutional\nnetwork to generate future frames given an input sequence. To deal with the\ninherently blurry predictions obtained from the standard Mean Squared Error\n(MSE) loss function, we propose three different and complementary feature\nlearning strategies: a multi-scale architecture, an adversarial training\nmethod, and an image gradient difference loss function. We compare our\npredictions to different published results based on recurrent neural networks\non the UCF101 dataset","url_abs":"http://arxiv.org/abs/1511.05440v6","url_pdf":"http://arxiv.org/pdf/1511.05440v6.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-multi-scale-video-prediction-beyond-mean","repo_url":"https://github.com/AdarshMJ/PredGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"deep-multi-scale-video-prediction-beyond-mean","repo_url":"https://github.com/coupriec/VideoPredictionICLR2016","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"deep-multi-scale-video-prediction-beyond-mean","repo_url":"https://github.com/dyelax/Adversarial_Video_Generation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deep-multi-scale-video-prediction-beyond-mean","repo_url":"https://github.com/liuem607/DYAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"deep-multi-scale-video-prediction-beyond-mean","repo_url":"https://github.com/wileyw/VideoGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"video-prediction","task_name":"Video Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1511.05440","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.05440"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/wileyw/VideoGAN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/liuem607/DYAN","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dyelax/Adversarial_Video_Generation","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AdarshMJ/PredGAN","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/coupriec/VideoPredictionICLR2016","reach":{"status":"ok","spdx":"GPL-3.0"}}],"summary":{"ran_draft_wrong":2,"unverified":8},"by_repo_kind":{"listed":{"samples":10,"ran":2,"repositories":2}},"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":"6058e7d6ba3bf3ef","entry":"clip_l2_diff","repo":"wileyw/VideoGAN","repo_kind":"listed","path":"process_data.py","file_url":"https://github.com/wileyw/VideoGAN/blob/HEAD/process_data.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6058e7d6ba3bf3ef"}},{"code_sha256_prefix":"be76e24e497297f1","entry":"crop_batch","repo":"wileyw/VideoGAN","repo_kind":"listed","path":"inference.py","file_url":"https://github.com/wileyw/VideoGAN/blob/HEAD/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"be76e24e497297f1"}},{"code_sha256_prefix":"ea03a354040c8006","entry":"b","repo":"dyelax/Adversarial_Video_Generation","repo_kind":"listed","path":"Code/tfutils.py","file_url":"https://github.com/dyelax/Adversarial_Video_Generation/blob/HEAD/Code/tfutils.py","link_basis":"harvester_set","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":"ea03a354040c8006"}},{"code_sha256_prefix":"7fbb509ee32c4723","entry":"conv_out_size","repo":"dyelax/Adversarial_Video_Generation","repo_kind":"listed","path":"Code/tfutils.py","file_url":"https://github.com/dyelax/Adversarial_Video_Generation/blob/HEAD/Code/tfutils.py","link_basis":"harvester_set","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":"7fbb509ee32c4723"}},{"code_sha256_prefix":"9f8a9b1faf0c144f","entry":"denormalize_frames","repo":"dyelax/Adversarial_Video_Generation","repo_kind":"listed","path":"Code/utils.py","file_url":"https://github.com/dyelax/Adversarial_Video_Generation/blob/HEAD/Code/utils.py","link_basis":"harvester_set","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":"9f8a9b1faf0c144f"}},{"code_sha256_prefix":"e83222ab4f55b7ad","entry":"get_dir","repo":"dyelax/Adversarial_Video_Generation","repo_kind":"listed","path":"Code/constants.py","file_url":"https://github.com/dyelax/Adversarial_Video_Generation/blob/HEAD/Code/constants.py","link_basis":"harvester_set","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":"e83222ab4f55b7ad"}},{"code_sha256_prefix":"98805789ae7fe83c","entry":"lp_loss","repo":"dyelax/Adversarial_Video_Generation","repo_kind":"listed","path":"Code/loss_functions.py","file_url":"https://github.com/dyelax/Adversarial_Video_Generation/blob/HEAD/Code/loss_functions.py","link_basis":"harvester_set","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":"98805789ae7fe83c"}},{"code_sha256_prefix":"1aa2d1529a141acb","entry":"normalize_frames","repo":"dyelax/Adversarial_Video_Generation","repo_kind":"listed","path":"Code/utils.py","file_url":"https://github.com/dyelax/Adversarial_Video_Generation/blob/HEAD/Code/utils.py","link_basis":"harvester_set","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":"1aa2d1529a141acb"}},{"code_sha256_prefix":"cc7ac26dfc006739","entry":"reconstruct_frame","repo":"wileyw/VideoGAN","repo_kind":"listed","path":"inference.py","file_url":"https://github.com/wileyw/VideoGAN/blob/HEAD/inference.py","link_basis":"first_harvest_node","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":"cc7ac26dfc006739"}},{"code_sha256_prefix":"77fde3d5c103dd8c","entry":"w","repo":"dyelax/Adversarial_Video_Generation","repo_kind":"listed","path":"Code/tfutils.py","file_url":"https://github.com/dyelax/Adversarial_Video_Generation/blob/HEAD/Code/tfutils.py","link_basis":"harvester_set","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":"77fde3d5c103dd8c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}