Papers › Stochastic Video Generation with a Learned Prior

Stochastic Video Generation with a Learned Prior

21 Feb 2018ICML 2018 7arXiv:1802.07687archive 2025-07-28

Emily Denton, Rob Fergus

Generating video frames that accurately predict future world states is challenging. Existing approaches either fail to capture the full distribution of outcomes, or yield blurry generations, or both. In this paper we introduce an unsupervised video generation model that learns a prior model of uncertainty in a given environment. Video frames are generated by drawing samples from this prior and combining them with a deterministic estimate of the future frame. The approach is simple and easily trained end-to-end on a variety of datasets. Sample generations are both varied and sharp, even many frames into the future, and compare favorably to those from existing approaches.

PaperPDFConference PDFCodeCode Syntology ran

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

By repository: official repository: 2 samples from 1 repository, 1 ran (0 with no instrument failure; 1 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.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

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

edenton/svg officialmentioned in papermentioned on GitHubpytorchSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
MIT-Omnipush/video-prediction mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Stochastic Adversarial Video Prediction (arXiv:1804.01523; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
joelouismarino/amortized-variational-filtering mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A General Method for Amortizing Variational Filtering (arXiv:1811.05090; that paper's own run record: 0 ran · 1 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

2 samples harvested: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure 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.

1ran · our draft was wrong
1unverified

Licence: 2 of the 2 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 edenton/svg. “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.

edenton/svg official repository 2 samples, 1 ran (1 instrument-failed) · 1 unverified
add_border generate_svg_lp.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 29e9a6b94f594378 · report fixture: signature x:Tensor/3/float, color:str/0/str, pad:int/0/int · returned Tensor · level recorded 2026-09-22
kl_criterion train_svg_lp.py unverified no licence file found · pointer only · 1353b420a1f9ed3f · report

Tasks

Video GenerationVideo Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Generation BAIR Robot Pushing SVG (from SRVP) Cond 2 #23 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing SVG (from SRVP) FVD score 255±4 #23 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing SVG (from SRVP) LPIPS 0.0609±0.0034 #23 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing SVG (from SRVP) PSNR 18.95±0.26 #23 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing SVG (from SRVP) Pred 28 #23 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing SVG (from SRVP) SSIM 0.8058±0.0088 #23 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing SVG (from SRVP) Train 12 #23 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing SVG-LP (from vRNN) Cond 2 #24 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing SVG-LP (from vRNN) FVD score 256.62 #24 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing SVG-LP (from vRNN) LPIPS 0.061±0.03 #24 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing SVG-LP (from vRNN) Pred 28 #24 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing SVG-LP (from vRNN) SSIM 0.816±0.07 #24 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing SVG-LP (from vRNN) Train 10 #24 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing SVG-FP (from FVD) Cond 2 #27 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing SVG-FP (from FVD) FVD score 315.5 #27 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing SVG-FP (from FVD) Pred 14 #27 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing SVG-FP (from FVD) Train 14 #27 of 31 Archive leaderboard report
Video Prediction Cityscapes 128x128 SVG (from Hier-VRNN) Cond. 2 #3 of 5 Archive leaderboard report
Video Prediction Cityscapes 128x128 SVG (from Hier-VRNN) FVD 1300.26 #3 of 5 Archive leaderboard report
Video Prediction Cityscapes 128x128 SVG (from Hier-VRNN) LPIPS 0.549 ± 0.06 #3 of 5 Archive leaderboard report
Video Prediction Cityscapes 128x128 SVG (from Hier-VRNN) Pred 28 #3 of 5 Archive leaderboard report
Video Prediction Cityscapes 128x128 SVG (from Hier-VRNN) SSIM 0.574±0.08 #3 of 5 Archive leaderboard report
Video Prediction Cityscapes 128x128 SVG (from Hier-VRNN) Train 10 #3 of 5 Archive leaderboard report
Video Prediction KTH SVG-LP (from Grid-keypoints) Cond 10 #3 of 31 Archive leaderboard report
Video Prediction KTH SVG-LP (from Grid-keypoints) FVD 157.9 #3 of 31 Archive leaderboard report
Video Prediction KTH SVG-LP (from Grid-keypoints) LPIPS 0.129 #3 of 31 Archive leaderboard report
Video Prediction KTH SVG-LP (from Grid-keypoints) PSNR 23.91 #3 of 31 Archive leaderboard report
Video Prediction KTH SVG-LP (from Grid-keypoints) Params (M) 22.8 #3 of 31 Archive leaderboard report
Video Prediction KTH SVG-LP (from Grid-keypoints) Pred 40 #3 of 31 Archive leaderboard report
Video Prediction KTH SVG-LP (from Grid-keypoints) SSIM 0.800 #3 of 31 Archive leaderboard report
Video Prediction KTH SVG-LP (from Grid-keypoints) Train 10 #3 of 31 Archive leaderboard report
Video Prediction KTH SVG-LP (from SRVP) Cond 10 #10 of 31 Archive leaderboard report
Video Prediction KTH SVG-LP (from SRVP) FVD 377 ± 6 #10 of 31 Archive leaderboard report
Video Prediction KTH SVG-LP (from SRVP) LPIPS 0.0923±0.0038 #10 of 31 Archive leaderboard report
Video Prediction KTH SVG-LP (from SRVP) PSNR 28.06±0.29 #10 of 31 Archive leaderboard report
Video Prediction KTH SVG-LP (from SRVP) Pred 30 #10 of 31 Archive leaderboard report
Video Prediction KTH SVG-LP (from SRVP) SSIM 0.8438±0.0054 #10 of 31 Archive leaderboard report
Video Prediction KTH SVG-LP (from SRVP) Train 10 #10 of 31 Archive leaderboard report
Video Prediction SynpickVP SVG-LP LPIPS 0.066 #4 of 5 Archive leaderboard report
Video Prediction SynpickVP SVG-LP MSE 51.82 #4 of 5 Archive leaderboard report
Video Prediction SynpickVP SVG-LP PSNR 27..38 #4 of 5 Archive leaderboard report
Video Prediction SynpickVP SVG-LP SSIM 0.886 #4 of 5 Archive leaderboard report
Video Prediction SynpickVP SVG-Det LPIPS 0.068 #5 of 5 Archive leaderboard report
Video Prediction SynpickVP SVG-Det MSE 60.60 #5 of 5 Archive leaderboard report
Video Prediction SynpickVP SVG-Det PSNR 26.92 #5 of 5 Archive leaderboard report
Video Prediction SynpickVP SVG-Det SSIM 0.879 #5 of 5 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.

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