Papers › MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation

MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation

19 May 2022arXiv:2205.09853archive 2025-07-28

Vikram Voleti, Alexia Jolicoeur-Martineau, Christopher Pal

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 ≤ 4 GPUs. Project page: https://mask-cond-video-diffusion.github.io ; Code : https://github.com/voletiv/mcvd-pytorch

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 16 code samples harvested from 2 repositories linked to this paper: 7 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 6 ran (3 with no instrument failure; 3 where Syntology's instrument failed); community (archive-listed): 5 samples from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

voletiv/mcvd-pytorch officialmentioned in papermentioned on GitHubpytorchSyntology: 11 samples, 6 ran (3 instrument-failed) · 5 unverified report
showlab/FAR mentioned on GitHubpytorchSyntology: 5 samples, 1 ran (0 instrument-failed) · 4 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

16 samples harvested: 7 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · our draft was wrong
1ran; the contract check could not run
4ran
9unverified

Licence: 0 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

voletiv/mcvd-pytorch official repository 11 samples, 6 ran (3 instrument-failed) · 5 unverified
Nin models/unet.py ran · metamorphic tier: invariant MIT (permissive) · fe8eda2d3c77b1ce · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
Normalize in 154 papers models/unet.py ran · our draft was wrong MIT (permissive) · 7a5794dd00d68985 · report fixture: signature num_channels:int/0/int · returned GroupNorm · level recorded 2026-09-22
Swish in 30 papers
census: 22 implementations from 19 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
models/unet.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · d0fc586d0b8f1592 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
Upsample in 77 papers models/unet.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · be28d1c32d65462b · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
get_timestep_embedding in 138 papers
census: 11 implementations from 15 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 1, kind int, dtype int64
models/unet.py ran; the contract check could not run (RAISES) MIT (permissive) · e3f5c3d286e3e169 · report fixture: signature timesteps:Tensor/1/int, embedding_dim:int/0/int · returned Tensor · level recorded 2026-09-22
partialclass in 13 papers models/unet.py ran · our draft was wrong MIT (permissive) · 61098cd5c9624563 · report fixture: signature cls:callable/0/?, args:tuple/1/int, kwds:dict/0/? · returned type · level recorded 2026-09-22
AttnBlock in 22 papers models/unet.py unverified MIT (permissive) · 608ce50c0a254bf3 · report
ResnetBlock in 49 papers models/unet.py unverified MIT (permissive) · b50ef756a12bcec1 · report
UNet in 40 papers models/unet.py unverified MIT (permissive) · 25b5bc70ae8eb1fe · report
default_init in 38 papers models/unet.py unverified MIT (permissive) · 90b0411e98af1284 · report
init_weights in 109 papers models/unet.py unverified MIT (permissive) · 356ce7450c78eec0 · report
showlab/FAR community (archive-listed) 5 samples, 1 ran (0 instrument-failed) · 4 unverified
AdaLayerNormZeroSingle far/models/far_model.py ran MIT (permissive) · c9e28313aeb3f410 · report fixture: returned AdaLayerNormZeroSingle · level recorded 2026-09-22
AdaLayerNormContinuous far/models/far_model.py unverified MIT (permissive) · 87c3ba7dfa415456 · report
FAR far/models/far_model.py unverified MIT (permissive) · c7f7d4ff2a1ca090 · report
FAR_AttnProcessor2_0 far/models/far_model.py unverified MIT (permissive) · f9bd59c7c4009713 · report
FAR_TransformerBlock far/models/far_model.py unverified MIT (permissive) · dd2836a2627dc893 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for Masked Conditional Video Diffusion (MCVD) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Masked Conditional Video Diffusion (MCVD) (graph method: Masked Conditional Video Diffusion (MCVD)). 5 bricks; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 2 siblings

  1. FAR entry · level 0 · unverified · c7f7d4ff2a1ca090
  2. AdaLayerNormContinuous helper · level 0 · unverified · 87c3ba7dfa415456
  3. FAR_TransformerBlock model · level 0 · unverified · dd2836a2627dc893
  4. AdaLayerNormZeroSingle helper · level 1 · ran · c9e28313aeb3f410
  5. FAR_AttnProcessor2_0 helper · level 0 · unverified · f9bd59c7c4009713

harvested Assembly for Masked Conditional Video Diffusion (MCVD) (graph method: Masked Conditional Video Diffusion (MCVD)). 11 bricks; individually on a fixture: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. UNet entry · level 0 · unverified · 25b5bc70ae8eb1fe
  2. AttnBlock model · level 0 · unverified · 608ce50c0a254bf3
  3. Normalize helper · level 1 · ran · our draft was wrong · 7a5794dd00d68985
  4. ResnetBlock model · level 0 · unverified · b50ef756a12bcec1
  5. Swish helper · level 1 · ran · d0fc586d0b8f1592
  6. Upsample model · level 1 · ran · be28d1c32d65462b
  7. get_timestep_embedding model · level 1 · ran; the contract check could not run (RAISES) · e3f5c3d286e3e169
  8. init_weights helper · level 0 · unverified · 356ce7450c78eec0
  9. partialclass helper · level 1 · ran · our draft was wrong · 61098cd5c9624563
  10. Nin helper · level 1 · ran · fe8eda2d3c77b1ce
  11. default_init helper · level 0 · unverified · 90b0411e98af1284

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2205.09853") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DenoisingPredictionVideo GenerationVideo Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Generation BAIR Robot Pushing MCVD : c2t5p14 Cond 2 #4 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing MCVD : c2t5p14 FVD score 87.9 #4 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing MCVD : c2t5p14 PSNR 19.1 #4 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing MCVD : c2t5p14 Pred 14 #4 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing MCVD : c2t5p14 SSIM 0.838 #4 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing MCVD : c2t5p14 Train 5 #4 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing MCVD : c1t5p15 Cond 1 #5 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing MCVD : c1t5p15 FVD score 89.5 #5 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing MCVD : c1t5p15 PSNR 16.9 #5 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing MCVD : c1t5p15 Pred 15 #5 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing MCVD : c1t5p15 SSIM 0.78 #5 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing MCVD : c1t5p15 Train 5 #5 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing MCVD : c2t5p28 Cond 2 #13 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing MCVD : c2t5p28 FVD score 118.4 #13 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing MCVD : c2t5p28 PSNR 16.2 #13 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing MCVD : c2t5p28 Pred 28 #13 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing MCVD : c2t5p28 SSIM 0.745 #13 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing MCVD : c2t5p28 Train 5 #13 of 31 Archive leaderboard report
Video Generation UCF-101 MCVD (64x64) FVD16 1143 #44 of 48 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Diffusion

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections