Papers › EDVR: Video Restoration with Enhanced Deformable Convolutional Networks

EDVR: Video Restoration with Enhanced Deformable Convolutional Networks

7 May 2019arXiv:1905.02716archive 2025-07-28

Xintao Wang, Kelvin C. K. Chan, Ke Yu, Chao Dong, Chen Change Loy

Video restoration tasks, including super-resolution, deblurring, etc, are drawing increasing attention in the computer vision community. A challenging benchmark named REDS is released in the NTIRE19 Challenge. This new benchmark challenges existing methods from two aspects: (1) how to align multiple frames given large motions, and (2) how to effectively fuse different frames with diverse motion and blur. In this work, we propose a novel Video Restoration framework with Enhanced Deformable networks, termed EDVR, to address these challenges. First, to handle large motions, we devise a Pyramid, Cascading and Deformable (PCD) alignment module, in which frame alignment is done at the feature level using deformable convolutions in a coarse-to-fine manner. Second, we propose a Temporal and Spatial Attention (TSA) fusion module, in which attention is applied both temporally and spatially, so as to emphasize important features for subsequent restoration. Thanks to these modules, our EDVR wins the champions and outperforms the second place by a large margin in all four tracks in the NTIRE19 video restoration and enhancement challenges. EDVR also demonstrates superior performance to state-of-the-art published methods on video super-resolution and deblurring. The code is available at https://github.com/xinntao/EDVR.

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="1905.02716")

Code

Syntology Ran 5 of 19 code samples harvested from 2 repositories linked to this paper; 14 have no recorded run. Of those that ran: 3 ran · our draft was wrong; 2 ran with no contract checked.

By repository: community (archive-listed): 19 samples from 2 repositories, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

xinntao/EDVR officialmentioned in papermentioned on GitHubpytorch report
Harrypotterrrr/EDVR mentioned on GitHubtf report
Pea-Shooter/ADNet mentioned on GitHubpytorchMIT report
YapengTian/TDAN-VSR-CVPR-2020 mentioned on GitHubpytorchMIT report
ZhaoHengrun/EDVR mentioned on GitHubpytorch report
drhdr-user/drhdr mentioned on GitHubpytorch report
khyeyoon/Video-Super-Resolution mentioned on GitHubpytorch report
liuzhen03/ADNet mentioned on GitHubpytorchMIT report
zhusiling/EDVR mentioned on GitHubpytorchApache-2.0 report
open-mmlab/mmsr pytorchApache-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

19 samples harvested; 5 ran; 0 honoured the contract we drafted; 14 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.

3ran · our draft was wrong
2ran
14unverified

Licence: 0 of the 19 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

calculate_psnr zhusiling/EDVR/codes/utils/util.py community (archive-listed) ran fingerprinted Apache-2.0 (permissive) · 9394ff2c25b8a988 · report
dict2str zhusiling/EDVR/codes/options/options.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · 40c52ad98161c17b · report
dict_to_nonedict zhusiling/EDVR/codes/options/options.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · ada7273eee7081c7 · report
flow_warp zhusiling/EDVR/codes/models/modules/module_util.py community (archive-listed) ran Apache-2.0 (permissive) · 7018e324f2150c43 · report
make_layer zhusiling/EDVR/codes/models/modules/module_util.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · c04a23de0531da4a · report
DUF_downsample zhusiling/EDVR/codes/utils/util.py community (archive-listed) unverified Apache-2.0 (permissive) · 30896d7c1646f28e · report
adapt_official zhusiling/EDVR/codes/models/modules/DUF_arch.py community (archive-listed) unverified Apache-2.0 (permissive) · a3c1e35e4ff68673 · report
check_exclude open-mmlab/mmsr/.dev_scripts/update_ut.py community (archive-listed) unverified Apache-2.0 (permissive) · eda5ede48a264b22 · report
collate_metrics open-mmlab/mmsr/.dev_scripts/utils/modelindex.py community (archive-listed) unverified Apache-2.0 (permissive) · 54b6d9dc8ce868bb · report
convert_data_config open-mmlab/mmsr/.dev_scripts/create_ceph_configs.py community (archive-listed) unverified Apache-2.0 (permissive) · 2c460a151351c467 · report
create_train_job_batch open-mmlab/mmsr/.dev_scripts/train_benchmark.py community (archive-listed) unverified Apache-2.0 (permissive) · cee4c863ad3de58e · report
filter_metric open-mmlab/mmsr/.dev_scripts/metric_mapping.py community (archive-listed) unverified Apache-2.0 (permissive) · 0ce4b91d8aca61e4 · report
found_table open-mmlab/mmsr/.dev_scripts/utils/modelindex.py community (archive-listed) unverified Apache-2.0 (permissive) · 8e5814637d5291d6 · report
parse zhusiling/EDVR/codes/options/options.py community (archive-listed) unverified Apache-2.0 (permissive) · ce4ad67a16f94299 · report
reading_image_worker zhusiling/EDVR/codes/data_scripts/create_lmdb_mp.py community (archive-listed) unverified Apache-2.0 (permissive) · e47a76b039b007e1 · report
start_from_proc open-mmlab/mmsr/.dev_scripts/job_watcher.py community (archive-listed) unverified Apache-2.0 (permissive) · 4214819cf4b6bd8d · report
tensor2img zhusiling/EDVR/codes/utils/util.py community (archive-listed) unverified Apache-2.0 (permissive) · 1b40b4f3f0ea0b6e · report
update_intervals open-mmlab/mmsr/.dev_scripts/create_ceph_configs.py community (archive-listed) unverified Apache-2.0 (permissive) · 4bbabfed79ffbff3 · report
update_md open-mmlab/mmsr/.dev_scripts/update_config_readme.py community (archive-listed) unverified Apache-2.0 (permissive) · 185156d990381282 · report

Tasks

DeblurringSuper-ResolutionVideo EnhancementVideo RestorationVideo Super-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Deblurring REDS EDVR_Deblur Average PSNR 34.80 #2 of 3 Archive leaderboard report
Video Enhancement MFQE v2 EDVR Incremental PSNR 0.75 #4 of 6 Archive leaderboard report
Video Super-Resolution Vid4 - 4x upscaling EDVR PSNR 27.35 #13 of 27 Archive leaderboard report
Video Super-Resolution Vid4 - 4x upscaling EDVR SSIM 0.8264 #13 of 27 Archive leaderboard report
Video Super-Resolution Vid4 - 4x upscaling - BD degradation EDVR PSNR 27.85 #10 of 18 Archive leaderboard report
Video Super-Resolution Vid4 - 4x upscaling - BD degradation EDVR SSIM 0.8503 #10 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.

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