Papers › Stochastic Latent Residual Video Prediction

Stochastic Latent Residual Video Prediction

21 Feb 2020ICML 2020 1arXiv:2002.09219archive 2025-07-28

Jean-Yves Franceschi, Edouard Delasalles, Mickaël Chen, Sylvain Lamprier, Patrick Gallinari

Designing video prediction models that account for the inherent uncertainty of the future is challenging. Most works in the literature are based on stochastic image-autoregressive recurrent networks, which raises several performance and applicability issues. An alternative is to use fully latent temporal models which untie frame synthesis and temporal dynamics. However, no such model for stochastic video prediction has been proposed in the literature yet, due to design and training difficulties. In this paper, we overcome these difficulties by introducing a novel stochastic temporal model whose dynamics are governed in a latent space by a residual update rule. This first-order scheme is motivated by discretization schemes of differential equations. It naturally models video dynamics as it allows our simpler, more interpretable, latent model to outperform prior state-of-the-art methods on challenging datasets.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2002.09219")

Code

Syntology Ran 2 of 12 code samples harvested from 1 repository linked to this paper; 10 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 1 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

edouardelasalles/srvp officialmentioned in papermentioned on GitHubpytorchApache-2.0 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

12 samples harvested; 2 ran; 0 honoured the contract we drafted; 10 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
1ran
10unverified

Licence: 0 of the 12 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 edouardelasalles/srvp. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

spatial_average edouardelasalles/srvp/metrics/lpips/networks_basic.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 29e5e72bcd006dcd · report
upsample edouardelasalles/srvp/metrics/lpips/networks_basic.py official repository ran fingerprinted Apache-2.0 (permissive) · 351677a36e1961df · report
activation_factory edouardelasalles/srvp/module/utils.py official repository unverified Apache-2.0 (permissive) · 75673c3489a5111c · report
l2 edouardelasalles/srvp/metrics/lpips/loss.py official repository unverified Apache-2.0 (permissive) · cebd4a767f96722b · report
load_json edouardelasalles/srvp/helper.py official repository unverified Apache-2.0 (permissive) · 1525ee5c735dc09b · report
load_yaml edouardelasalles/srvp/helper.py official repository unverified Apache-2.0 (permissive) · 2e294d738f6cc876 · report
make_normal_from_raw_params edouardelasalles/srvp/module/utils.py official repository unverified Apache-2.0 (permissive) · df7836d4e167b95e · report
normalize_tensor edouardelasalles/srvp/metrics/lpips/loss.py official repository unverified Apache-2.0 (permissive) · 15df2c2c65353c11 · report
psnr edouardelasalles/srvp/metrics/lpips/loss.py official repository unverified Apache-2.0 (permissive) · e844cf206c6621e3 · report
rsample_normal edouardelasalles/srvp/module/utils.py official repository unverified Apache-2.0 (permissive) · f202199f0213bab0 · report
score_2afc_dataset edouardelasalles/srvp/metrics/lpips/dist_model.py official repository unverified Apache-2.0 (permissive) · dfd2379e29a03aef · report
score_jnd_dataset edouardelasalles/srvp/metrics/lpips/dist_model.py official repository unverified Apache-2.0 (permissive) · 2cdf9c19c6aff6a0 · report

Tasks

PredictionVideo GenerationVideo Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Generation BAIR Robot Pushing SRVP Cond 2 #21 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing SRVP FVD score 162 ± 4 #21 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing SRVP LPIPS 0.0574±0.0032 #21 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing SRVP PSNR 19.59±0.27 #21 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing SRVP Pred 28 #21 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing SRVP SSIM 0.8196±0.0084 #21 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing SRVP Train 12 #21 of 31 Archive leaderboard report
Video Prediction Cityscapes 128x128 SRVP Cond. 10 #5 of 5 Archive leaderboard report
Video Prediction Cityscapes 128x128 SRVP LPIPS 0.447±0.014 #5 of 5 Archive leaderboard report
Video Prediction Cityscapes 128x128 SRVP PSNR 20.97±0.43 #5 of 5 Archive leaderboard report
Video Prediction Cityscapes 128x128 SRVP Pred 20 #5 of 5 Archive leaderboard report
Video Prediction Cityscapes 128x128 SRVP SSIM 0.603±0.016 #5 of 5 Archive leaderboard report
Video Prediction KTH SRVP Cond 10 #6 of 31 Archive leaderboard report
Video Prediction KTH SRVP FVD 222 ± 3 #6 of 31 Archive leaderboard report
Video Prediction KTH SRVP LPIPS 0.0736±0.0029 #6 of 31 Archive leaderboard report
Video Prediction KTH SRVP PSNR 29.69±032 #6 of 31 Archive leaderboard report
Video Prediction KTH SRVP Pred 30 #6 of 31 Archive leaderboard report
Video Prediction KTH SRVP SSIM 0.8697±0.0046 #6 of 31 Archive leaderboard report
Video Prediction KTH SRVP Train 10 #6 of 31 Archive leaderboard report
Video Prediction KTH 64x64 cond10 pred30 SRVP FVD 222 #1 of 1 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