Papers › Recurrent Video Restoration Transformer with Guided Deformable Attention

Recurrent Video Restoration Transformer with Guided Deformable Attention

5 Jun 2022arXiv:2206.02146archive 2025-07-28

Jingyun Liang, Yuchen Fan, Xiaoyu Xiang, Rakesh Ranjan, Eddy Ilg, Simon Green, JieZhang Cao, Kai Zhang, Radu Timofte, Luc van Gool

Video restoration aims at restoring multiple high-quality frames from multiple low-quality frames. Existing video restoration methods generally fall into two extreme cases, i.e., they either restore all frames in parallel or restore the video frame by frame in a recurrent way, which would result in different merits and drawbacks. Typically, the former has the advantage of temporal information fusion. However, it suffers from large model size and intensive memory consumption; the latter has a relatively small model size as it shares parameters across frames; however, it lacks long-range dependency modeling ability and parallelizability. In this paper, we attempt to integrate the advantages of the two cases by proposing a recurrent video restoration transformer, namely RVRT. RVRT processes local neighboring frames in parallel within a globally recurrent framework which can achieve a good trade-off between model size, effectiveness, and efficiency. Specifically, RVRT divides the video into multiple clips and uses the previously inferred clip feature to estimate the subsequent clip feature. Within each clip, different frame features are jointly updated with implicit feature aggregation. Across different clips, the guided deformable attention is designed for clip-to-clip alignment, which predicts multiple relevant locations from the whole inferred clip and aggregates their features by the attention mechanism. Extensive experiments on video super-resolution, deblurring, and denoising show that the proposed RVRT achieves state-of-the-art performance on benchmark datasets with balanced model size, testing memory and runtime.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 14 code samples harvested from 2 repositories linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 9 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 5 samples from 1 repository, 4 ran (0 with no instrument failure; 4 where Syntology's instrument failed); community (archive-listed): 9 samples from 1 repository, 8 ran (3 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

jingyunliang/rvrt officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: 5 samples, 4 ran (4 instrument-failed) · 1 unverified report
Ascend-Research/Turtle mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning Truncated Causal History Model for Video Restoration (arXiv:2410.03936; that paper's own run record: 7 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
labshuhanggu/mia-vsr mentioned on GitHubpytorchApache-2.0Syntology: 9 samples, 8 ran (5 instrument-failed) · 1 unverified report
xg416/DATUM mentioned on GitHubpytorchSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

14 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 9 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

6ran · our draft was wrong
3ran; the contract check could not run
3ran
2unverified

Licence: 7 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. 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; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

jingyunliang/rvrt official repository 5 samples, 4 ran (4 instrument-failed) · 1 unverified
flow_warp in 48 papers models/network_rvrt.py ran · our draft was wrong licence not identified · pointer only · 0c02fb4e80bda186 · report fixture: signature x:Tensor/4/float, flow:Tensor/4/float, interp_mode:str/0/str, padding_mode:str/0/str, align_corners:bool/0/bool · returned Tensor · level recorded 2026-09-22
make_layer in 76 papers models/network_rvrt.py ran · our draft was wrong licence not identified · pointer only · b80adc256b420252 · report fixture: signature block:callable/0/?, num_blocks:int/0/int, in_channels:int/0/int, out_channels:int/0/int, kernel_size:int/0/int · returned Sequential · level recorded 2026-09-22
test_video main_test_rvrt.py ran · our draft was wrong licence not identified · pointer only · a1cad82b9beff0c7 · report fixture: signature lq:Tensor/5/float, model:callable/0/?, args:Args/0/? · returned Tensor · level recorded 2026-09-22
window_partition in 377 papers
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 5, kind float, dtype float32
models/network_rvrt.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant licence not identified · pointer only · 54da2d24c1765483 · report fixture: signature x:Tensor/5/float, window_size:tuple/1/int · returned Tensor · level recorded 2026-09-22
test_clip main_test_rvrt.py unverified licence not identified · pointer only · 705758eeba9070e3 · report
labshuhanggu/mia-vsr community (archive-listed) 9 samples, 8 ran (5 instrument-failed) · 1 unverified
batch_index_fill archs/functions.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 7839fb1aca0933e2 · report fixture: signature x:Tensor/3/float, x1:Tensor/3/float, x2:Tensor/3/float, idx1:Tensor/2/int, idx2:Tensor/2/int · returned Tensor · level recorded 2026-09-22
batch_index_select in 13 papers archs/functions.py ran Apache-2.0 (permissive) · 6bc3966389f69fe9 · report fixture: signature x:Tensor/3/float, idx:Tensor/2/int · returned Tensor · level recorded 2026-09-24
drop_path in 325 papers
census: 27 implementations from 61 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32
archs/mia_sliding_arch.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant Apache-2.0 (permissive) · 52d96aa31ed74a56 · report fixture: signature x:Tensor/4/float, drop_prob:float/0/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-22
flow_warp_avg_patch archs/mia_vsr_arch.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 9e66eec08eeb6369 · report fixture: signature x:Tensor/4/float, flow:Tensor/4/float, interpolation:str/0/str, padding_mode:str/0/str, align_corners:bool/0/bool · returned Tensor · level recorded 2026-09-22
reduce_loss in 75 papers losses/loss_util.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · a648a03a952822c0 · report fixture: signature loss:Tensor/2/float, reduction:str/0/str · returned Tensor · level recorded 2026-09-26
weight_reduce_loss in 61 papers losses/loss_util.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 1ba39317ea81871a · report fixture: signature loss:Tensor/2/float, weight:Tensor/2/float, reduction:str/0/str · returned Tensor · level recorded 2026-09-26
window_partition in 377 papers
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
archs/mia_sliding_arch.py ran Apache-2.0 (permissive) · e0f3c2fd11d92ad7 · report fixture: signature x:Tensor/5/float, window_size:tuple/1/int · returned Tensor · level recorded 2026-09-24
window_single_partition archs/mia_sliding_arch.py ran Apache-2.0 (permissive) · c0dc7488e394219c · report fixture: signature x:Tensor/4/float, window_size:tuple/1/int · returned Tensor · level recorded 2026-09-24
weighted_loss in 53 papers losses/loss_util.py unverified Apache-2.0 (permissive) · cf63f8afc13f62a7 · report

Tasks

Analog Video RestorationDeblurringDenoisingSnow RemovalSuper-ResolutionVideo DenoisingVideo RestorationVideo Super-ResolutionVideo deraining

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Analog Video Restoration TAPE RVRT LPIPS 0.117 #4 of 7 Archive leaderboard report
Analog Video Restoration TAPE RVRT PSNR 32.47 #4 of 7 Archive leaderboard report
Analog Video Restoration TAPE RVRT SSIM 0.896 #4 of 7 Archive leaderboard report
Analog Video Restoration TAPE RVRT VMAF 72.41 #4 of 7 Archive leaderboard report
Deblurring DVD RVRT PSNR 34.92 #2 of 7 Archive leaderboard report
Deblurring DVD RVRT SSIM 97.38 #2 of 7 Archive leaderboard report
Video Denoising DAVIS sigma10 RVRT PSNR 40.57 #3 of 6 Archive leaderboard report
Video Denoising DAVIS sigma20 RVRT PSNR 38.05 #3 of 7 Archive leaderboard report
Video Denoising DAVIS sigma30 RVRT PSNR 36.57 #2 of 7 Archive leaderboard report
Video Denoising DAVIS sigma40 RVRT PSNR 35.47 #2 of 8 Archive leaderboard report
Video Denoising DAVIS sigma50 RVRT PSNR 34.57 #2 of 8 Archive leaderboard report
Video Denoising Set8 sigma10 RVRT PSNR 37.53 #3 of 6 Archive leaderboard report
Video Denoising Set8 sigma20 RVRT PSNR 34.83 #3 of 7 Archive leaderboard report
Video Denoising Set8 sigma30 RVRT PSNR 33.3 #3 of 7 Archive leaderboard report
Video Denoising Set8 sigma40 RVRT PSNR 32.21 #2 of 8 Archive leaderboard report
Video Denoising Set8 sigma50 RVRT PSNR 31.33 #2 of 9 Archive leaderboard report
Video Super-Resolution UDM10 - 4x upscaling RVRT PSNR 40.9 #2 of 7 Archive leaderboard report
Video Super-Resolution UDM10 - 4x upscaling RVRT SSIM 0.9729 #2 of 7 Archive leaderboard report
Video Super-Resolution Vid4 - 4x upscaling RVRT PSNR 27.99 #7 of 27 Archive leaderboard report
Video Super-Resolution Vid4 - 4x upscaling RVRT SSIM 0.8462 #7 of 27 Archive leaderboard report
Video Super-Resolution Vid4 - 4x upscaling - BD degradation RVRT PSNR 29.54 #1 of 18 Archive leaderboard report
Video Super-Resolution Vid4 - 4x upscaling - BD degradation RVRT SSIM 0.8810 #1 of 18 Archive leaderboard report
Video Super-Resolution Vimeo90K RVRT PSNR 38.59 #2 of 3 Archive leaderboard report
Video Super-Resolution Vimeo90K RVRT SSIM 0.9576 #2 of 3 Archive leaderboard report
Video deraining VRDS RVRT PSNR 28.24 #8 of 8 Archive leaderboard report
Video deraining VRDS RVRT SSIM 0.8857 #8 of 8 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

CLIP

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