{"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/masked-conditional-video-diffusion-for","title":"MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation","arxiv_id":"2205.09853","date":"2022-05-19","proceeding":null,"authors":["Vikram Voleti","Alexia Jolicoeur-Martineau","Christopher Pal"],"abstract":"Video prediction is a challenging task. The quality of video frames from current state-of-the-art (SOTA) generative models tends to be poor and generalization beyond the training data is difficult. Furthermore, existing prediction frameworks are typically not capable of simultaneously handling other video-related tasks such as unconditional generation or interpolation. In this work, we devise a general-purpose framework called Masked Conditional Video Diffusion (MCVD) for all of these video synthesis tasks using a probabilistic conditional score-based denoising diffusion model, conditioned on past and/or future frames. We train the model in a manner where we randomly and independently mask all the past frames or all the future frames. This novel but straightforward setup allows us to train a single model that is capable of executing a broad range of video tasks, specifically: future/past prediction -- when only future/past frames are masked; unconditional generation -- when both past and future frames are masked; and interpolation -- when neither past nor future frames are masked. Our experiments show that this approach can generate high-quality frames for diverse types of videos. Our MCVD models are built from simple non-recurrent 2D-convolutional architectures, conditioning on blocks of frames and generating blocks of frames. We generate videos of arbitrary lengths autoregressively in a block-wise manner. Our approach yields SOTA results across standard video prediction and interpolation benchmarks, with computation times for training models measured in 1-12 days using $\\le$ 4 GPUs. Project page: https://mask-cond-video-diffusion.github.io ; Code : https://github.com/voletiv/mcvd-pytorch","url_abs":"https://arxiv.org/abs/2205.09853v4","url_pdf":"https://arxiv.org/pdf/2205.09853v4.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":"masked-conditional-video-diffusion-for","repo_url":"https://github.com/voletiv/mcvd-pytorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"masked-conditional-video-diffusion-for","repo_url":"https://github.com/showlab/FAR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"video-generation","task_name":"Video Generation"},{"task_slug":"video-prediction","task_name":"Video Prediction"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-generation-on-bair-robot-pushing","task":"Video Generation","dataset":"BAIR Robot Pushing","model":"MCVD : c2t5p14","rank_in_archive_order":4,"of":31,"metrics":{"Cond":"2","FVD score":"87.9","PSNR":"19.1","Pred":"14","SSIM":"0.838","Train":"5"},"uses_additional_data":false},{"leaderboard":"/sota/video-generation-on-bair-robot-pushing","task":"Video Generation","dataset":"BAIR Robot Pushing","model":"MCVD : c1t5p15","rank_in_archive_order":5,"of":31,"metrics":{"Cond":"1","FVD score":"89.5","PSNR":"16.9","Pred":"15","SSIM":"0.78","Train":"5"},"uses_additional_data":false},{"leaderboard":"/sota/video-generation-on-bair-robot-pushing","task":"Video Generation","dataset":"BAIR Robot Pushing","model":"MCVD : c2t5p28","rank_in_archive_order":13,"of":31,"metrics":{"Cond":"2","FVD score":"118.4","PSNR":"16.2","Pred":"28","SSIM":"0.745","Train":"5"},"uses_additional_data":false},{"leaderboard":"/sota/video-generation-on-ucf-101","task":"Video Generation","dataset":"UCF-101","model":"MCVD (64x64)","rank_in_archive_order":44,"of":48,"metrics":{"FVD16":"1143"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2205.09853","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.09853"}},"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/voletiv/mcvd-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/showlab/FAR","reach":null}],"summary":{"ran":5,"ran_draft_wrong":1,"ran_fixture":1,"unverified":9},"by_repo_kind":{"official":{"samples":11,"ran":6,"repositories":1},"listed":{"samples":5,"ran":1,"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":"c9e28313aeb3f410","entry":"AdaLayerNormZeroSingle","repo":"showlab/FAR","repo_kind":"listed","path":"far/models/far_model.py","file_url":"https://github.com/showlab/FAR/blob/HEAD/far/models/far_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c9e28313aeb3f410"}},{"code_sha256_prefix":"fe8eda2d3c77b1ce","entry":"Nin","repo":"voletiv/mcvd-pytorch","repo_kind":"official","path":"models/unet.py","file_url":"https://github.com/voletiv/mcvd-pytorch/blob/HEAD/models/unet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fe8eda2d3c77b1ce"}},{"code_sha256_prefix":"7a5794dd00d68985","entry":"Normalize","repo":"voletiv/mcvd-pytorch","repo_kind":"official","path":"models/unet.py","file_url":"https://github.com/voletiv/mcvd-pytorch/blob/HEAD/models/unet.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7a5794dd00d68985"}},{"code_sha256_prefix":"d0fc586d0b8f1592","entry":"Swish","repo":"voletiv/mcvd-pytorch","repo_kind":"official","path":"models/unet.py","file_url":"https://github.com/voletiv/mcvd-pytorch/blob/HEAD/models/unet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d0fc586d0b8f1592"}},{"code_sha256_prefix":"be28d1c32d65462b","entry":"Upsample","repo":"voletiv/mcvd-pytorch","repo_kind":"official","path":"models/unet.py","file_url":"https://github.com/voletiv/mcvd-pytorch/blob/HEAD/models/unet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"be28d1c32d65462b"}},{"code_sha256_prefix":"e3f5c3d286e3e169","entry":"get_timestep_embedding","repo":"voletiv/mcvd-pytorch","repo_kind":"official","path":"models/unet.py","file_url":"https://github.com/voletiv/mcvd-pytorch/blob/HEAD/models/unet.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e3f5c3d286e3e169"}},{"code_sha256_prefix":"61098cd5c9624563","entry":"partialclass","repo":"voletiv/mcvd-pytorch","repo_kind":"official","path":"models/unet.py","file_url":"https://github.com/voletiv/mcvd-pytorch/blob/HEAD/models/unet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"61098cd5c9624563"}},{"code_sha256_prefix":"87c3ba7dfa415456","entry":"AdaLayerNormContinuous","repo":"showlab/FAR","repo_kind":"listed","path":"far/models/far_model.py","file_url":"https://github.com/showlab/FAR/blob/HEAD/far/models/far_model.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":"87c3ba7dfa415456"}},{"code_sha256_prefix":"608ce50c0a254bf3","entry":"AttnBlock","repo":"voletiv/mcvd-pytorch","repo_kind":"official","path":"models/unet.py","file_url":"https://github.com/voletiv/mcvd-pytorch/blob/HEAD/models/unet.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":"608ce50c0a254bf3"}},{"code_sha256_prefix":"c7f7d4ff2a1ca090","entry":"FAR","repo":"showlab/FAR","repo_kind":"listed","path":"far/models/far_model.py","file_url":"https://github.com/showlab/FAR/blob/HEAD/far/models/far_model.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":"c7f7d4ff2a1ca090"}},{"code_sha256_prefix":"f9bd59c7c4009713","entry":"FAR_AttnProcessor2_0","repo":"showlab/FAR","repo_kind":"listed","path":"far/models/far_model.py","file_url":"https://github.com/showlab/FAR/blob/HEAD/far/models/far_model.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":"f9bd59c7c4009713"}},{"code_sha256_prefix":"dd2836a2627dc893","entry":"FAR_TransformerBlock","repo":"showlab/FAR","repo_kind":"listed","path":"far/models/far_model.py","file_url":"https://github.com/showlab/FAR/blob/HEAD/far/models/far_model.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":"dd2836a2627dc893"}},{"code_sha256_prefix":"b50ef756a12bcec1","entry":"ResnetBlock","repo":"voletiv/mcvd-pytorch","repo_kind":"official","path":"models/unet.py","file_url":"https://github.com/voletiv/mcvd-pytorch/blob/HEAD/models/unet.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":"b50ef756a12bcec1"}},{"code_sha256_prefix":"25b5bc70ae8eb1fe","entry":"UNet","repo":"voletiv/mcvd-pytorch","repo_kind":"official","path":"models/unet.py","file_url":"https://github.com/voletiv/mcvd-pytorch/blob/HEAD/models/unet.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":"25b5bc70ae8eb1fe"}},{"code_sha256_prefix":"90b0411e98af1284","entry":"default_init","repo":"voletiv/mcvd-pytorch","repo_kind":"official","path":"models/unet.py","file_url":"https://github.com/voletiv/mcvd-pytorch/blob/HEAD/models/unet.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":"90b0411e98af1284"}},{"code_sha256_prefix":"356ce7450c78eec0","entry":"init_weights","repo":"voletiv/mcvd-pytorch","repo_kind":"official","path":"models/unet.py","file_url":"https://github.com/voletiv/mcvd-pytorch/blob/HEAD/models/unet.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":"356ce7450c78eec0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}