Papers › BSRT: Improving Burst Super-Resolution with Swin Transformer and Flow-Guided...

BSRT: Improving Burst Super-Resolution with Swin Transformer and Flow-Guided Deformable Alignment

18 Apr 2022arXiv:2204.08332archive 2025-07-28

Ziwei Luo, Youwei Li, Shen Cheng, Lei Yu, Qi Wu, Zhihong Wen, Haoqiang Fan, Jian Sun, Shuaicheng Liu

This work addresses the Burst Super-Resolution (BurstSR) task using a new architecture, which requires restoring a high-quality image from a sequence of noisy, misaligned, and low-resolution RAW bursts. To overcome the challenges in BurstSR, we propose a Burst Super-Resolution Transformer (BSRT), which can significantly improve the capability of extracting inter-frame information and reconstruction. To achieve this goal, we propose a Pyramid Flow-Guided Deformable Convolution Network (Pyramid FG-DCN) and incorporate Swin Transformer Blocks and Groups as our main backbone. More specifically, we combine optical flows and deformable convolutions, hence our BSRT can handle misalignment and aggregate the potential texture information in multi-frames more efficiently. In addition, our Transformer-based structure can capture long-range dependency to further improve the performance. The evaluation on both synthetic and real-world tracks demonstrates that our approach achieves a new state-of-the-art in BurstSR task. Further, our BSRT wins the championship in the NTIRE2022 Burst Super-Resolution Challenge.

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="2204.08332")

Code

Syntology Ran 5 of 13 code samples harvested from 1 repository linked to this paper; 8 have no recorded run. Of those that ran: 1 ran · honoured contract; 3 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: official repository: 13 samples from 1 repository, 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.

algolzw/bsrt officialmentioned in papermentioned on GitHubpytorchMIT 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

13 samples harvested; 5 ran; 1 honoured the contract we drafted; 8 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.

1ran · honoured contract
3ran · our draft was wrong
1ran · fixture could not drive it
8unverified

Licence: 0 of the 13 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 algolzw/bsrt. “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.

window_partition algolzw/bsrt/code/real/bsrt/model/swin_util.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 144d10b49baeb8a6 · report
default_conv algolzw/bsrt/code/real/bsrt/model/common.py official repository ran · our draft was wrong MIT (permissive) · 8b0e794d4d8f9b13 · report
gaussian algolzw/bsrt/code/real/bsrt/loss/mssim.py official repository ran · honoured contract fingerprinted MIT (permissive) · c56b7ef16f309a45 · report
make_layer algolzw/bsrt/code/real/bsrt/model/arch_util.py official repository ran · our draft was wrong MIT (permissive) · c04a23de0531da4a · report
window_reverse algolzw/bsrt/code/real/bsrt/model/swin_util.py official repository ran · our draft was wrong MIT (permissive) · 61bf152e6a42a184 · report
calculate_mask algolzw/bsrt/code/real/bsrt/model/swin_util.py official repository unverified MIT (permissive) · 4207be9abb47f822 · report
conv_layer algolzw/bsrt/code/real/bsrt/model/arch_util.py official repository unverified MIT (permissive) · 12673020c3dd4547 · report
create_window algolzw/bsrt/code/real/bsrt/loss/mssim.py official repository unverified MIT (permissive) · 443341084ce76798 · report
detach_variable algolzw/bsrt/code/real/bsrt/model/checkpoint.py official repository unverified MIT (permissive) · 0164a82edf7c189a · report
lanczos_kernel algolzw/bsrt/code/real/bsrt/model/common.py official repository unverified MIT (permissive) · ce51ac527b1a8912 · report
lanczos_shift algolzw/bsrt/code/real/bsrt/model/common.py official repository unverified MIT (permissive) · cbfba08000a4b667 · report
make_layer_idx algolzw/bsrt/code/real/bsrt/model/arch_util.py official repository unverified MIT (permissive) · b630516ce93f40f9 · report
ssim algolzw/bsrt/code/real/bsrt/loss/mssim.py official repository unverified MIT (permissive) · 8bcd6627e53013bf · report

Tasks

Burst Image ReconstructionBurst Image Super-ResolutionMulti-Frame Super-ResolutionOptical Flow EstimationSuper-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Burst Image Super-Resolution BurstSR BSRT-Large LPIPS 0.021 #3 of 9 Archive leaderboard report
Burst Image Super-Resolution BurstSR BSRT-Large PSNR 48.57 #3 of 9 Archive leaderboard report
Burst Image Super-Resolution BurstSR BSRT-Large SSIM 0.986 #3 of 9 Archive leaderboard report
Burst Image Super-Resolution BurstSR BSRT-Small LPIPS 0.021 #5 of 9 Archive leaderboard report
Burst Image Super-Resolution BurstSR BSRT-Small PSNR 48.48 #5 of 9 Archive leaderboard report
Burst Image Super-Resolution BurstSR BSRT-Small SSIM 0.985 #5 of 9 Archive leaderboard report
Burst Image Super-Resolution SyntheticBurst BSRT-Large LPIPS 0.025 #1 of 8 Archive leaderboard report
Burst Image Super-Resolution SyntheticBurst BSRT-Large PSNR 43.62 #1 of 8 Archive leaderboard report
Burst Image Super-Resolution SyntheticBurst BSRT-Large SSIM 0.975 #1 of 8 Archive leaderboard report
Burst Image Super-Resolution SyntheticBurst BSRT-Small LPIPS 0.031 #4 of 8 Archive leaderboard report
Burst Image Super-Resolution SyntheticBurst BSRT-Small PSNR 42.72 #4 of 8 Archive leaderboard report
Burst Image Super-Resolution SyntheticBurst BSRT-Small SSIM 0.971 #4 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

Absolute Position EncodingsAdamAttentionBPEConvolutionDeformable ConvolutionDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxStochastic DepthSwin TransformerTransformer

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