Papers › Deep Blind Video Super-resolution

Deep Blind Video Super-resolution

10 Mar 2020ICCV 2021 10arXiv:2003.04716archive 2025-07-28

Jinshan Pan, Songsheng Cheng, Jiawei Zhang, Jinhui Tang

Existing video super-resolution (SR) algorithms usually assume that the blur kernels in the degradation process are known and do not model the blur kernels in the restoration. However, this assumption does not hold for video SR and usually leads to over-smoothed super-resolved images. In this paper, we propose a deep convolutional neural network (CNN) model to solve video SR by a blur kernel modeling approach. The proposed deep CNN model consists of motion blur estimation, motion estimation, and latent image restoration modules. The motion blur estimation module is used to provide reliable blur kernels. With the estimated blur kernel, we develop an image deconvolution method based on the image formation model of video SR to generate intermediate latent images so that some sharp image contents can be restored well. However, the generated intermediate latent images may contain artifacts. To generate high-quality images, we use the motion estimation module to explore the information from adjacent frames, where the motion estimation can constrain the deep CNN model for better image restoration. We show that the proposed algorithm is able to generate clearer images with finer structural details. Extensive experimental results show that the proposed algorithm performs favorably against state-of-the-art methods.

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="2003.04716")

Code

Syntology Ran 9 of 15 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 2 ran · honoured contract; 1 ran · our draft was wrong; 6 ran with no contract checked.

By repository: official repository: 15 samples from 1 repository, 9 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

csbhr/Deep-Blind-VSR officialpytorchMIT report
cscss/DBVSR mentioned 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

15 samples harvested; 9 ran; 2 honoured the contract we drafted; 6 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.

2ran · honoured contract
1ran · our draft was wrong
6ran
6unverified

Licence: 0 of the 15 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 csbhr/Deep-Blind-VSR. “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.

Backward csbhr/Deep-Blind-VSR/code/model/flow_pwc.py official repository ran MIT (permissive) · 8509275d3bfff1d0 · report
c2c csbhr/Deep-Blind-VSR/code/model/utils_fft.py official repository ran · honoured contract fingerprinted MIT (permissive) · 30e7c61b0ccdb5ad · report
get_act csbhr/Deep-Blind-VSR/code/model/blocks.py official repository ran MIT (permissive) · 9d45f748f3832a1f · report
get_norm csbhr/Deep-Blind-VSR/code/model/blocks.py official repository ran MIT (permissive) · d4d29aac211d1ccc · report
get_same_padding csbhr/Deep-Blind-VSR/code/model/blocks.py official repository ran fingerprinted MIT (permissive) · 4ec1f46edd412686 · report
kernel2png csbhr/Deep-Blind-VSR/code/script_gene_dataset.py official repository ran MIT (permissive) · 36142f054164f733 · report
matlab_style_gauss2D csbhr/Deep-Blind-VSR/code/script_gene_dataset.py official repository ran MIT (permissive) · 28ff9e1e5937defa · report
r2c csbhr/Deep-Blind-VSR/code/model/utils_fft.py official repository ran · honoured contract fingerprinted MIT (permissive) · 3a47878a83b2d0ed · report
splits csbhr/Deep-Blind-VSR/code/model/utils_fft.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · bb9dc6b4b21ead20 · report
cupy_kernel csbhr/Deep-Blind-VSR/code/model/correlation/correlation.py official repository unverified MIT (permissive) · 262657b0ce1b117c · report
deconv_batch csbhr/Deep-Blind-VSR/code/model/deconv_fft.py official repository unverified MIT (permissive) · 337e4fc810c76e0b · report
deconv_sisr_L2_fft csbhr/Deep-Blind-VSR/code/model/deconv_fft.py official repository unverified MIT (permissive) · 6fee3d72011125ca · report
get_blur_kernel csbhr/Deep-Blind-VSR/code/script_gene_dataset.py official repository unverified MIT (permissive) · 2d06bc62983ab57c · report
make_model csbhr/Deep-Blind-VSR/code/model/flow_pwc.py official repository unverified MIT (permissive) · 3d1acf751ad881a5 · report
make_model csbhr/Deep-Blind-VSR/code/model/kernel.py official repository unverified MIT (permissive) · ee5cd3a09717005c · report

Tasks

Image DeconvolutionImage RestorationMotion EstimationSuper-ResolutionVideo Super-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Super-Resolution MSU Super-Resolution for Video Compression DBVSR + vvenc BSQ-rate over ERQA 15.988 #42 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression DBVSR + vvenc BSQ-rate over LPIPS 11.435 #42 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression DBVSR + vvenc BSQ-rate over MS-SSIM 0.898 #42 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression DBVSR + vvenc BSQ-rate over PSNR 5.765 #42 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression DBVSR + vvenc BSQ-rate over Subjective Score 2.842 #42 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression DBVSR + vvenc BSQ-rate over VMAF 0.698 #42 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression DBVSR + x264 BSQ-rate over ERQA 1.606 #48 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression DBVSR + x264 BSQ-rate over LPIPS 1.293 #48 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression DBVSR + x264 BSQ-rate over MS-SSIM 0.714 #48 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression DBVSR + x264 BSQ-rate over PSNR 1.082 #48 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression DBVSR + x264 BSQ-rate over VMAF 0.75 #48 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression DBVSR + uavs3e BSQ-rate over ERQA 7.0 #57 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression DBVSR + uavs3e BSQ-rate over LPIPS 4.371 #57 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression DBVSR + uavs3e BSQ-rate over MS-SSIM 2.396 #57 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression DBVSR + uavs3e BSQ-rate over PSNR 5.845 #57 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression DBVSR + uavs3e BSQ-rate over VMAF 1.83 #57 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression DBVSR + x265 BSQ-rate over ERQA 13.145 #65 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression DBVSR + x265 BSQ-rate over LPIPS 13.211 #65 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression DBVSR + x265 BSQ-rate over MS-SSIM 1.438 #65 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression DBVSR + x265 BSQ-rate over PSNR 6.607 #65 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression DBVSR + x265 BSQ-rate over VMAF 1.383 #65 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression DBVSR + aomenc BSQ-rate over ERQA 13.476 #69 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression DBVSR + aomenc BSQ-rate over LPIPS 4.916 #69 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression DBVSR + aomenc BSQ-rate over MS-SSIM 3.886 #69 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression DBVSR + aomenc BSQ-rate over PSNR 10.296 #69 of 85 Archive leaderboard report
Video Super-Resolution MSU Super-Resolution for Video Compression DBVSR + aomenc BSQ-rate over VMAF 2.093 #69 of 85 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration DBVSR 1 - LPIPS 0.921 #4 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration DBVSR ERQAv1.0 0.737 #4 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration DBVSR FPS 0.241 #4 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration DBVSR PSNR 31.071 #4 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration DBVSR QRCRv1.0 0.629 #4 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration DBVSR SSIM 0.894 #4 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration DBVSR Subjective score 6.947 #4 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Upscalers: Quality Enhancement DBVSR PSNR 27.28 #45 of 48 Archive leaderboard report
Video Super-Resolution MSU Video Upscalers: Quality Enhancement DBVSR SSIM 0.937 #45 of 48 Archive leaderboard report
Video Super-Resolution MSU Video Upscalers: Quality Enhancement DBVSR VMAF 57.39 #45 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