Papers › Revisiting Temporal Modeling for Video Super-resolution

Revisiting Temporal Modeling for Video Super-resolution

13 Aug 2020arXiv:2008.05765archive 2025-07-28

Takashi Isobe, Fang Zhu, Xu Jia, Shengjin Wang

Video super-resolution plays an important role in surveillance video analysis and ultra-high-definition video display, which has drawn much attention in both the research and industrial communities. Although many deep learning-based VSR methods have been proposed, it is hard to directly compare these methods since the different loss functions and training datasets have a significant impact on the super-resolution results. In this work, we carefully study and compare three temporal modeling methods (2D CNN with early fusion, 3D CNN with slow fusion and Recurrent Neural Network) for video super-resolution. We also propose a novel Recurrent Residual Network (RRN) for efficient video super-resolution, where residual learning is utilized to stabilize the training of RNN and meanwhile to boost the super-resolution performance. Extensive experiments show that the proposed RRN is highly computational efficiency and produces temporal consistent VSR results with finer details than other temporal modeling methods. Besides, the proposed method achieves state-of-the-art results on several widely used benchmarks.

PaperPDFCodeCode 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="2008.05765")

Code

Syntology Ran 0 of 2 code samples harvested from 1 repository linked to this paper; 2 have no recorded run.

By repository: community (archive-listed): 2 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

junpan19/RRN officialmentioned in paperpytorch report
mediatek-neuropilot/mai22-real-time-video-sr mentioned on GitHubtfApache-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

2 samples harvested; 0 ran; 0 honoured the contract we drafted; 2 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.

2unverified

Licence: 0 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 mediatek-neuropilot/mai22-real-time-video-sr. “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.

is_subclass mediatek-neuropilot/mai22-real-time-video-sr/util/common_util.py community (archive-listed) unverified Apache-2.0 (permissive) · 62dbff7b7b234c59 · report
make_layer mediatek-neuropilot/mai22-real-time-video-sr/model/mobile_rrn.py community (archive-listed) unverified Apache-2.0 (permissive) · 800ed13a7c7bf194 · report

Tasks

Computational EfficiencySuper-ResolutionVideo Super-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration RRN-10L 1 - LPIPS 0.842 #15 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration RRN-10L ERQAv1.0 0.627 #15 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration RRN-10L FPS 2.567 #15 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration RRN-10L PSNR 24.252 #15 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration RRN-10L QRCRv1.0 0.557 #15 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration RRN-10L SSIM 0.79 #15 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration RRN-10L Subjective score 5.35 #15 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration RRN-5L 1 - LPIPS 0.856 #20 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration RRN-5L ERQAv1.0 0.617 #20 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration RRN-5L FPS 2.74 #20 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration RRN-5L PSNR 23.786 #20 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration RRN-5L QRCRv1.0 0.549 #20 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration RRN-5L SSIM 0.789 #20 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration RRN-5L Subjective score 5.02 #20 of 32 Archive leaderboard report
Video Super-Resolution SPMCS - 4x upscaling RRN-L PSNR 29.84 #1 of 1 Archive leaderboard report
Video Super-Resolution SPMCS - 4x upscaling RRN-L SSIM 0.8690 #1 of 1 Archive leaderboard report
Video Super-Resolution UDM10 - 4x upscaling RRN-L PSNR 38.97 #7 of 7 Archive leaderboard report
Video Super-Resolution UDM10 - 4x upscaling RRN-L SSIM 0.9534 #7 of 7 Archive leaderboard report
Video Super-Resolution Vid4 - 4x upscaling - BD degradation RRN PSNR 27.69 #11 of 18 Archive leaderboard report
Video Super-Resolution Vid4 - 4x upscaling - BD degradation RRN SSIM 0.8488 #11 of 18 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

3D CNN

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