Papers › Blur-aware Spatio-temporal Sparse Transformer for Video Deblurring

Blur-aware Spatio-temporal Sparse Transformer for Video Deblurring

11 Jun 2024CVPR 2024 1arXiv:2406.07551archive 2025-07-28

Huicong Zhang, Haozhe Xie, Hongxun Yao

Video deblurring relies on leveraging information from other frames in the video sequence to restore the blurred regions in the current frame. Mainstream approaches employ bidirectional feature propagation, spatio-temporal transformers, or a combination of both to extract information from the video sequence. However, limitations in memory and computational resources constraints the temporal window length of the spatio-temporal transformer, preventing the extraction of longer temporal contextual information from the video sequence. Additionally, bidirectional feature propagation is highly sensitive to inaccurate optical flow in blurry frames, leading to error accumulation during the propagation process. To address these issues, we propose \textbf{BSSTNet}, \textbf{B}lur-aware \textbf{S}patio-temporal \textbf{S}parse \textbf{T}ransformer Network. It introduces the blur map, which converts the originally dense attention into a sparse form, enabling a more extensive utilization of information throughout the entire video sequence. Specifically, BSSTNet (1) uses a longer temporal window in the transformer, leveraging information from more distant frames to restore the blurry pixels in the current frame. (2) introduces bidirectional feature propagation guided by blur maps, which reduces error accumulation caused by the blur frame. The experimental results demonstrate the proposed BSSTNet outperforms the state-of-the-art methods on the GoPro and DVD datasets.

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="2406.07551")

Code

Syntology Ran 10 of 17 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 5 ran · our draft was wrong; 5 ran with no contract checked.

By repository: official repository: 17 samples from 1 repository, 10 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

huicongzhang/bsstnet officialmentioned in paperpytorch 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

17 samples harvested; 10 ran; 0 honoured the contract we drafted; 7 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.

5ran · our draft was wrong
5ran
7unverified

Licence: 17 of the 17 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 huicongzhang/bsstnet. “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.

TernaryLoss huicongzhang/bsstnet/basicsr/utils/flow_loss.py official repository ran no licence file found · pointer only · c2e12a1d35bc95f1 · report
conv huicongzhang/bsstnet/basicsr/archs/gshift_arch.py official repository ran · our draft was wrong no licence file found · pointer only · ad4c565716dab068 · report
conv1x1 huicongzhang/bsstnet/basicsr/archs/gshift_arch.py official repository ran · our draft was wrong no licence file found · pointer only · 9bed061f167dd318 · report
fbConsistencyCheck huicongzhang/bsstnet/basicsr/archs/BSST_arch.py official repository ran no licence file found · pointer only · 538e6221204076af · report
flow_warp huicongzhang/bsstnet/basicsr/archs/BSST_arch.py official repository ran · our draft was wrong no licence file found · pointer only · 0c02fb4e80bda186 · report
get_position_from_periods huicongzhang/bsstnet/basicsr/models/lr_scheduler.py official repository ran fingerprinted no licence file found · pointer only · cd569444547de84f · report
image_warp huicongzhang/bsstnet/basicsr/utils/flow_loss.py official repository ran fingerprinted no licence file found · pointer only · b48d437fd5dc2844 · report
length_sq huicongzhang/bsstnet/basicsr/archs/BSST_arch.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · 99919ce37333a615 · report
make_layer huicongzhang/bsstnet/basicsr/archs/arch_util.py official repository ran · our draft was wrong no licence file found · pointer only · 96ad5dc9ca239aec · report
resize_flow huicongzhang/bsstnet/basicsr/archs/arch_util.py official repository ran no licence file found · pointer only · 5a1d8458dc7077a6 · report
FlowLoss huicongzhang/bsstnet/basicsr/utils/flow_loss.py official repository unverified no licence file found · pointer only · 612cc86afbc665c9 · report
g_path_regularize huicongzhang/bsstnet/basicsr/losses/gan_loss.py official repository unverified no licence file found · pointer only · fe05416387de89c6 · report
gradient_penalty_loss huicongzhang/bsstnet/basicsr/losses/gan_loss.py official repository unverified no licence file found · pointer only · 81eb425a41a7c2a1 · report
r1_penalty huicongzhang/bsstnet/basicsr/losses/gan_loss.py official repository unverified no licence file found · pointer only · 73446c7004a4a9cb · report
reduce_loss huicongzhang/bsstnet/basicsr/losses/loss_util.py official repository unverified no licence file found · pointer only · a648a03a952822c0 · report
weight_reduce_loss huicongzhang/bsstnet/basicsr/losses/loss_util.py official repository unverified no licence file found · pointer only · 1ba39317ea81871a · report
weighted_loss huicongzhang/bsstnet/basicsr/losses/loss_util.py official repository unverified no licence file found · pointer only · cf63f8afc13f62a7 · report

Tasks

DeblurringOptical Flow EstimationVideo Deblurring

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Deblurring DVD BSSTNet PSNR 34.95 #1 of 7 Archive leaderboard report
Deblurring DVD BSSTNet SSIM 0.9703 #1 of 7 Archive leaderboard report
Deblurring GoPro BSSTNet PSNR 35.98 #1 of 56 Archive leaderboard report
Deblurring GoPro BSSTNet SSIM 0.9792 #1 of 56 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