Papers › COMISR: Compression-Informed Video Super-Resolution

COMISR: Compression-Informed Video Super-Resolution

4 May 2021ICCV 2021 10arXiv:2105.01237archive 2025-07-28

Yinxiao Li, Pengchong Jin, Feng Yang, Ce Liu, Ming-Hsuan Yang, Peyman Milanfar

Most video super-resolution methods focus on restoring high-resolution video frames from low-resolution videos without taking into account compression. However, most videos on the web or mobile devices are compressed, and the compression can be severe when the bandwidth is limited. In this paper, we propose a new compression-informed video super-resolution model to restore high-resolution content without introducing artifacts caused by compression. The proposed model consists of three modules for video super-resolution: bi-directional recurrent warping, detail-preserving flow estimation, and Laplacian enhancement. All these three modules are used to deal with compression properties such as the location of the intra-frames in the input and smoothness in the output frames. For thorough performance evaluation, we conducted extensive experiments on standard datasets with a wide range of compression rates, covering many real video use cases. We showed that our method not only recovers high-resolution content on uncompressed frames from the widely-used benchmark datasets, but also achieves state-of-the-art performance in super-resolving compressed videos based on numerous quantitative metrics. We also evaluated the proposed method by simulating streaming from YouTube to demonstrate its effectiveness and robustness. The source codes and trained models are available at https://github.com/google-research/google-research/tree/master/comisr.

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="2105.01237")

Code

Syntology Ran 0 of 3 code samples harvested from 1 repository linked to this paper; 3 have no recorded run.

By repository: official repository: 3 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.

google-research/google-research officialmentioned in papertf 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

3 samples harvested; 0 ran; 0 honoured the contract we drafted; 3 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.

3unverified

Licence: 0 of the 3 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 google-research/google-research. “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.

generator_f google-research/google-research/comisr/lib/model.py official repository unverified Apache-2.0 (permissive) · 62dd1717d6103648 · report
generator_f_decoder google-research/google-research/comisr/lib/model.py official repository unverified Apache-2.0 (permissive) · e77c35357f58bd9b · report
generator_f_encoder google-research/google-research/comisr/lib/model.py official repository unverified Apache-2.0 (permissive) · fa51e5712feb334b · report

Tasks

Super-ResolutionVideo Super-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Super-Resolution MSU Super-Resolution for Video Compression COMISR + x264 BSQ-rate over ERQA 0.969 #6 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression COMISR + x264 BSQ-rate over LPIPS 1.118 #6 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression COMISR + x264 BSQ-rate over MS-SSIM 0.672 #6 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression COMISR + x264 BSQ-rate over PSNR 6.081 #6 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression COMISR + x264 BSQ-rate over Subjective Score 0.367 #6 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression COMISR + x264 BSQ-rate over VMAF 1.302 #6 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression COMISR + vvenc BSQ-rate over ERQA 13.246 #11 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression COMISR + vvenc BSQ-rate over LPIPS 11.026 #11 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression COMISR + vvenc BSQ-rate over MS-SSIM 6.024 #11 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression COMISR + vvenc BSQ-rate over PSNR 11.497 #11 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression COMISR + vvenc BSQ-rate over Subjective Score 0.701 #11 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression COMISR + vvenc BSQ-rate over VMAF 8.105 #11 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression COMISR + x265 BSQ-rate over ERQA 8.139 #13 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression COMISR + x265 BSQ-rate over LPIPS 12.998 #13 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression COMISR + x265 BSQ-rate over MS-SSIM 4.793 #13 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression COMISR + x265 BSQ-rate over PSNR 10.678 #13 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression COMISR + x265 BSQ-rate over Subjective Score 0.741 #13 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression COMISR + x265 BSQ-rate over VMAF 6.363 #13 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression COMISR + uavs3e BSQ-rate over ERQA 3.427 #16 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression COMISR + uavs3e BSQ-rate over LPIPS 3.851 #16 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression COMISR + uavs3e BSQ-rate over MS-SSIM 7.711 #16 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression COMISR + uavs3e BSQ-rate over PSNR 5.761 #16 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression COMISR + uavs3e BSQ-rate over Subjective Score 1.229 #16 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression COMISR + uavs3e BSQ-rate over VMAF 9.47 #16 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression COMISR + aomenc BSQ-rate over ERQA 11.177 #26 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression COMISR + aomenc BSQ-rate over LPIPS 4.801 #26 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression COMISR + aomenc BSQ-rate over MS-SSIM 11.303 #26 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression COMISR + aomenc BSQ-rate over PSNR 15.144 #26 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression COMISR + aomenc BSQ-rate over Subjective Score 1.943 #26 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression COMISR + aomenc BSQ-rate over VMAF 10.67 #26 of 85 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration COMISR 1 - LPIPS 0.879 #9 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration COMISR ERQAv1.0 0.654 #9 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration COMISR FPS 1.613 #9 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration COMISR PSNR 26.708 #9 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration COMISR QRCRv1.0 0.619 #9 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration COMISR SSIM 0.84 #9 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration COMISR Subjective score 5.637 #9 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Upscalers: Quality Enhancement COMISR LPIPS 0.291 #21 of 48 Archive leaderboard report
Video Super-Resolution MSU Video Upscalers: Quality Enhancement COMISR PSNR 30.97 #21 of 48 Archive leaderboard report
Video Super-Resolution MSU Video Upscalers: Quality Enhancement COMISR SSIM 0.871 #21 of 48 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