Papers › Learning Temporal Coherence via Self-Supervision for GAN-based Video Generation

Learning Temporal Coherence via Self-Supervision for GAN-based Video Generation

23 Nov 2018arXiv:1811.09393archive 2025-07-28

Mengyu Chu, You Xie, Jonas Mayer, Laura Leal-Taixé, Nils Thuerey

Our work explores temporal self-supervision for GAN-based video generation tasks. While adversarial training successfully yields generative models for a variety of areas, temporal relationships in the generated data are much less explored. Natural temporal changes are crucial for sequential generation tasks, e.g. video super-resolution and unpaired video translation. For the former, state-of-the-art methods often favor simpler norm losses such as L² over adversarial training. However, their averaging nature easily leads to temporally smooth results with an undesirable lack of spatial detail. For unpaired video translation, existing approaches modify the generator networks to form spatio-temporal cycle consistencies. In contrast, we focus on improving learning objectives and propose a temporally self-supervised algorithm. For both tasks, we show that temporal adversarial learning is key to achieving temporally coherent solutions without sacrificing spatial detail. We also propose a novel Ping-Pong loss to improve the long-term temporal consistency. It effectively prevents recurrent networks from accumulating artifacts temporally without depressing detailed features. Additionally, we propose a first set of metrics to quantitatively evaluate the accuracy as well as the perceptual quality of the temporal evolution. A series of user studies confirm the rankings computed with these metrics. Code, data, models, and results are provided at https://github.com/thunil/TecoGAN. The project page https://ge.in.tum.de/publications/2019-tecogan-chu/ contains supplemental materials.

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 25 code samples harvested from 4 repositories linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 14 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 19 samples from 1 repository, 9 ran (9 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 6 samples from 3 repositories, 2 ran (0 with no instrument failure; 2 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 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

13 repositories listed; official and paper-mentioned ones first.

thunil/TecoGAN officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 19 samples, 9 ran (0 instrument-failed) · 10 unverified report
DwightFoster/Pytorch-TecoGan mentioned on GitHubpytorchSyntology: not harvested report
Fuhui-Chen/TecoGAN mentioned on GitHubpytorchApache-2.0Syntology: 1 sample, 0 ran · 1 unverified report
GitHubXlong/TecoGAN mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
HERMINDERSINGH1234/ML_Extra_Resolution_Increases mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
JonathanLehner/TecoGan-downloader mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
MLX15/TecoGAN mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
adbobes/VideoSuperResolution mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Spectral Normalization for Generative Adversarial Networks (arXiv:1802.05957; that paper's own run record: 25 ran (of which 9 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 1 violated, 20 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
sdxone/resolution mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
tom-doerr/TecoGAN mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
tom-doerr/TecoGAN-Docker mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
vscoboy/AI- mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
zhusiling/TecoGAN mentioned on GitHubpytorchApache-2.0Syntology: 3 samples, 0 ran · 3 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.

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

25 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 14 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
9ran
14unverified

Licence: 0 of the 25 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 4 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.

thunil/TecoGAN official repository 19 samples, 9 ran (0 instrument-failed) · 10 unverified
deprocess in 13 papers lib/ops.py ran fingerprinted Apache-2.0 (permissive) · 4288f8e325eb43a4 · report fixture: signature image:EagerTensor/4/float · returned SymbolicTensor · level recorded 2026-09-25
inference_data_loader lib/dataloader.py ran Apache-2.0 (permissive) · f1f42c8d72e93bc7 · report fixture: signature FLAGS:callable/0/? · returned Data · level recorded 2026-09-25
listPNGinDir metrics.py ran Apache-2.0 (permissive) · 18b708b43f329c07 · report fixture: signature dirpath:str/0/str · returned list · level recorded 2026-09-25
preprocess in 284 papers
census: 11 implementations from 13 papers, 10 distinct outputs across 5 buckets, one shared input per bucket
lib/ops.py ran fingerprinted Apache-2.0 (permissive) · 7b296d580bba710b · report fixture: signature image:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-25
preprocessLR lib/ops.py ran fingerprinted Apache-2.0 (permissive) · 36508e74f93db68d · report fixture: signature image:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-25
psnr in 88 papers
census: 9 implementations from 11 papers, 6 distinct outputs across 4 buckets, one shared input per bucket
metrics.py ran fingerprinted Apache-2.0 (permissive) · c3bb172480fc8386 · report fixture: signature img_true:ndarray/3/float, img_pred:ndarray/3/float · returned float64 · level recorded 2026-09-25
rand_flip in 6 papers LPIPSmodels/util.py ran fingerprinted Apache-2.0 (permissive) · 63d90e9c640f8ddc · report fixture: signature input1:ndarray/1/int, input2:ndarray/1/int · returned tuple · level recorded 2026-09-25
score_2afc_dataset in 18 papers LPIPSmodels/dist_model.py ran Apache-2.0 (permissive) · 3f3c7f753146a949 · report fixture: signature data_loader:MinimalDataLoader/0/?, func:callable/0/? · returned tuple · level recorded 2026-09-25
to_uint8 metrics.py ran Apache-2.0 (permissive) · 1886de70aee9a73c · report fixture: signature x:ndarray/2/int, vmin:int/0/int, vmax:int/0/int · returned ndarray · level recorded 2026-09-25
TecoGAN lib/Teco.py unverified Apache-2.0 (permissive) · b63ceffc84988277 · report
VGG19_slim lib/Teco.py unverified Apache-2.0 (permissive) · 32689cfcac75fba7 · report
bootstrap in 11 papers LPIPSmodels/util.py unverified Apache-2.0 (permissive) · e5bd7d84ecd3318d · report
discriminator_F lib/Teco.py unverified Apache-2.0 (permissive) · f9613204ac33adac · report
fnet lib/frvsr.py unverified Apache-2.0 (permissive) · b8657455e1ad6e8c · report
generator_F lib/frvsr.py unverified Apache-2.0 (permissive) · 11bc1870e570c529 · report
loadHR lib/dataloader.py unverified Apache-2.0 (permissive) · e8e48aaabe4bfc7a · report
loadHR_batch lib/dataloader.py unverified Apache-2.0 (permissive) · cb5f6a4cb024caf8 · report
read_text_file in 11 papers LPIPSmodels/util.py unverified Apache-2.0 (permissive) · 276eacceee671652 · report
score_jnd_dataset in 10 papers LPIPSmodels/dist_model.py unverified Apache-2.0 (permissive) · ff4f1d08f3459a4e · report
Fuhui-Chen/TecoGAN community (archive-listed) 1 sample, 0 ran · 1 unverified
TecoGAN Lib/Teco.py unverified Apache-2.0 (permissive) · 3cdddb5eb30c9d4e · report
sdxone/resolution community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
folder_check runGan.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 2514cc4783c71a9e · report fixture: signature path:str/0/str · returned str · level recorded 2026-09-22
mycall runGan.py ran · our draft was wrong Apache-2.0 (permissive) · 38b58f617f0d12eb · report fixture: signature cmd:list/1/str, block:bool/0/bool · returned Popen · level recorded 2026-09-22
zhusiling/TecoGAN community (archive-listed) 3 samples, 0 ran · 3 unverified
TecoGAN lib/Teco.py unverified Apache-2.0 (permissive) · 7046ec3be0229a9b · report
loadHR lib/dataloader.py unverified Apache-2.0 (permissive) · 92dd998a9c3eacfc · report
loadHR_batch lib/dataloader.py unverified Apache-2.0 (permissive) · ff20179ab53fa4dc · report

Tasks

Image Super-ResolutionMotion CompensationSuper-ResolutionTranslationVideo GenerationVideo Super-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Super-Resolution MSU Video Upscalers: Quality Enhancement TecoGAN PSNR 26.60 #42 of 48 Archive leaderboard report
Video Super-Resolution MSU Video Upscalers: Quality Enhancement TecoGAN SSIM 0.933 #42 of 48 Archive leaderboard report
Video Super-Resolution MSU Video Upscalers: Quality Enhancement TecoGAN VMAF 61.20 #42 of 48 Archive leaderboard report
Video Super-Resolution Vid4 - 4x upscaling TecoGAN⊖ PSNR 25.89 #26 of 27 Archive leaderboard report
Video Super-Resolution Vid4 - 4x upscaling TecoGAN PSNR 25.57 #27 of 27 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