Papers › Temporal Modulation Network for Controllable Space-Time Video Super-Resolution

Temporal Modulation Network for Controllable Space-Time Video Super-Resolution

21 Apr 2021CVPR 2021 1arXiv:2104.10642archive 2025-07-28

Gang Xu, Jun Xu, Zhen Li, Liang Wang, Xing Sun, Ming-Ming Cheng

Space-time video super-resolution (STVSR) aims to increase the spatial and temporal resolutions of low-resolution and low-frame-rate videos. Recently, deformable convolution based methods have achieved promising STVSR performance, but they could only infer the intermediate frame pre-defined in the training stage. Besides, these methods undervalued the short-term motion cues among adjacent frames. In this paper, we propose a Temporal Modulation Network (TMNet) to interpolate arbitrary intermediate frame(s) with accurate high-resolution reconstruction. Specifically, we propose a Temporal Modulation Block (TMB) to modulate deformable convolution kernels for controllable feature interpolation. To well exploit the temporal information, we propose a Locally-temporal Feature Comparison (LFC) module, along with the Bi-directional Deformable ConvLSTM, to extract short-term and long-term motion cues in videos. Experiments on three benchmark datasets demonstrate that our TMNet outperforms previous STVSR methods. The code is available at https://github.com/CS-GangXu/TMNet.

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="2104.10642")

Code

Syntology Ran 1 of 6 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 1 ran with no contract checked.

By repository: official repository: 6 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

CS-GangXu/TMNet officialmentioned in papermentioned on GitHubpytorch 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

6 samples harvested; 1 ran; 0 honoured the contract we drafted; 5 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
5unverified

Licence: 0 of the 6 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 CS-GangXu/TMNet. “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.

TMB CS-GangXu/TMNet/models/modules/STVSR.py official repository ran Apache-2.0 (permissive) · 1c814131165d7ef0 · report
BiDeformableConvLSTM CS-GangXu/TMNet/models/modules/STVSR.py official repository unverified Apache-2.0 (permissive) · 43ed322f20337c3b · report
DeformableConvLSTM CS-GangXu/TMNet/models/modules/STVSR.py official repository unverified Apache-2.0 (permissive) · 8cdc0946aaa23d7a · report
Easy_PCD CS-GangXu/TMNet/models/modules/STVSR.py official repository unverified Apache-2.0 (permissive) · e4122e785ab49435 · report
PCD_Align CS-GangXu/TMNet/models/modules/STVSR.py official repository unverified Apache-2.0 (permissive) · f6dd4f92cf1e6361 · report
TMNet CS-GangXu/TMNet/models/modules/STVSR.py official repository unverified Apache-2.0 (permissive) · 1dec0a72229da15f · report

Tasks

Space-time Video Super-resolutionSuper-ResolutionVideo Super-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Super-Resolution MSU Super-Resolution for Video Compression TMNet + x264 BSQ-rate over ERQA 1.879 #50 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression TMNet + x264 BSQ-rate over LPIPS 1.377 #50 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression TMNet + x264 BSQ-rate over MS-SSIM 0.844 #50 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression TMNet + x264 BSQ-rate over PSNR 1.481 #50 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression TMNet + x264 BSQ-rate over VMAF 1.061 #50 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression TMNet + uavs3e BSQ-rate over ERQA 13.187 #66 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression TMNet + uavs3e BSQ-rate over LPIPS 5.015 #66 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression TMNet + uavs3e BSQ-rate over MS-SSIM 4.317 #66 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression TMNet + uavs3e BSQ-rate over PSNR 15.144 #66 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression TMNet + uavs3e BSQ-rate over VMAF 3.487 #66 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression TMNet + x265 BSQ-rate over ERQA 13.577 #70 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression TMNet + x265 BSQ-rate over LPIPS 13.485 #70 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression TMNet + x265 BSQ-rate over MS-SSIM 1.735 #70 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression TMNet + x265 BSQ-rate over PSNR 7.046 #70 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression TMNet + x265 BSQ-rate over VMAF 2.009 #70 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression TMNet + vvenc BSQ-rate over ERQA 21.303 #80 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression TMNet + vvenc BSQ-rate over LPIPS 13.988 #80 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression TMNet + vvenc BSQ-rate over MS-SSIM 1.813 #80 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression TMNet + vvenc BSQ-rate over PSNR 9.43 #80 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression TMNet + vvenc BSQ-rate over VMAF 1.795 #80 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression TMNet + aomenc BSQ-rate over ERQA 21.798 #81 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression TMNet + aomenc BSQ-rate over LPIPS 6.276 #81 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression TMNet + aomenc BSQ-rate over MS-SSIM 10.322 #81 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression TMNet + aomenc BSQ-rate over PSNR 15.144 #81 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression TMNet + aomenc BSQ-rate over VMAF 4.667 #81 of 85 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration TMNet 1 - LPIPS 0.931 #8 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration TMNet ERQAv1.0 0.712 #8 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration TMNet FPS 1.136 #8 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration TMNet PSNR 30.364 #8 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration TMNet QRCRv1.0 0.549 #8 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration TMNet SSIM 0.885 #8 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration TMNet Subjective score 6 #8 of 32 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

ConvLSTMConvolutionDeformable ConvolutionSigmoid ActivationTanh Activation

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