Papers › Towards Real-World Burst Image Super-Resolution: Benchmark and Method

Towards Real-World Burst Image Super-Resolution: Benchmark and Method

9 Sep 2023ICCV 2023 1arXiv:2309.04803archive 2025-07-28

Pengxu Wei, Yujing Sun, Xingbei Guo, Chang Liu, Jie Chen, Xiangyang Ji, Liang Lin

Despite substantial advances, single-image super-resolution (SISR) is always in a dilemma to reconstruct high-quality images with limited information from one input image, especially in realistic scenarios. In this paper, we establish a large-scale real-world burst super-resolution dataset, i.e., RealBSR, to explore the faithful reconstruction of image details from multiple frames. Furthermore, we introduce a Federated Burst Affinity network (FBAnet) to investigate non-trivial pixel-wise displacements among images under real-world image degradation. Specifically, rather than using pixel-wise alignment, our FBAnet employs a simple homography alignment from a structural geometry aspect and a Federated Affinity Fusion (FAF) strategy to aggregate the complementary information among frames. Those fused informative representations are fed to a Transformer-based module of burst representation decoding. Besides, we have conducted extensive experiments on two versions of our datasets, i.e., RealBSR-RAW and RealBSR-RGB. Experimental results demonstrate that our FBAnet outperforms existing state-of-the-art burst SR methods and also achieves visually-pleasant SR image predictions with model details. Our dataset, codes, and models are publicly available at https://github.com/yjsunnn/FBANet.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 29 code samples harvested from 1 repository linked to this paper: 22 ran (of which 11 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 1 violated, 14 with no contract checked; 6 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 29 samples from 1 repository, 22 ran (16 with no instrument failure; 6 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.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 22 samples that ran has no recorded date.

yjsunnn/fbanet officialmentioned in paperpytorchMITSyntology: 29 samples, 22 ran (6 instrument-failed) · 7 unverified 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

29 samples harvested: 22 ran (of which 11 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 1 violated, 14 with no contract checked; 6 where Syntology's instrument failed) · 7 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.

1ran · honoured contract
1ran · violated contract
5ran · our draft was wrong
1ran; the contract check could not run
14ran
7unverified

Licence: 5 of the 29 samples are pointer only, meaning Syntology does not serve that copy's text. For 5 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 yjsunnn/fbanet. “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”. For 5 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

yjsunnn/fbanet official repository 29 samples, 22 ran (6 instrument-failed) · 7 unverified
ConvProjection model.py ran MIT (permissive) · ac174fec3e23aa7b · report fixture: returned ConvProjection · level recorded 2026-09-22
Downsample_flatten model.py ran fingerprinted MIT (permissive) · 323265751addf553 · report fixture: returned Downsample_flatten · level recorded 2026-09-22
LeFF model.py ran MIT (permissive) · 77ff7b6704558111 · report fixture: returned LeFF · level recorded 2026-09-22
LinearProjection model.py ran MIT (permissive) · 8cc07c7cf8e3296d · report fixture: returned LinearProjection · level recorded 2026-09-22
LinearProjection_Concat_kv model.py ran MIT (permissive) · a88d832a42153fba · report fixture: returned LinearProjection_Concat_kv · level recorded 2026-09-22
ResBlock in 127 papers
census: 6 implementations from 5 papers, 6 distinct outputs across 2 buckets, one shared input per bucket
model.py ran fingerprinted MIT (permissive) · b72b66e9ec7fe38f · report fixture: returned ResBlock · level recorded 2026-09-22
SEBasicBlock model.py ran MIT (permissive) · 01718b15b1a6769a · report fixture: returned SEBasicBlock · level recorded 2026-09-22
SepConv2d model.py ran fingerprinted MIT (permissive) · 3cfb6d8134fa5a62 · report fixture: returned SepConv2d · level recorded 2026-09-22
Upsample in 77 papers model.py ran MIT (permissive) · 93f3d523e11ee887 · report fixture: returned Upsample · level recorded 2026-09-22
Upsample_flatten model.py ran MIT (permissive) · a1f6b98b451f9950 · report fixture: returned Upsample_flatten · level recorded 2026-09-22
Upsampler model.py ran MIT (permissive) · 71266d282079ed33 · report fixture: returned Upsampler · level recorded 2026-09-22
calculate_parameters utils/calculate_parameters.py ran MIT (permissive) · 8f2cb62f2e2829d6 · report fixture: signature model:callable/0/? · returned int · level recorded 2026-09-24
conv3x3 in 1,376 papers model.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 583f9780bdd00a45 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded 2026-09-22
default_conv in 70 papers common.py ran · our draft was wrong MIT (permissive) · 8b0e794d4d8f9b13 · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, kernel_size:int/0/int, bias:bool/0/bool · returned Conv2d · level recorded 2026-09-22
get_crop ManualDataset.py ran MIT (permissive) · 8c20aac2b589f3ab · report fixture: signature img:Tensor/3/float, r1:int/0/int, r2:int/0/int, c1:int/0/int, c2:int/0/int · returned Tensor · level recorded 2026-09-24
get_pad_layer in 25 papers utils/antialias.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 50aa4a59fe718c61 · report fixture: signature pad_type:str/0/str · returned type · level recorded, date not recorded
get_pad_layer_1d in 9 papers utils/antialias.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 176a539246e68879 · report fixture: signature pad_type:str/0/str · returned type · level recorded 2026-09-24
is_frozen in 10 papers utils/model_utils.py ran · violated contract MIT (permissive) here; the stored copy is pointer only · 930cddf0a4d80ab1 · report fixture: signature model:callable/0/? · returned bool · level recorded 2026-09-24
load_start_epoch in 9 papers utils/model_utils.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · c3bea8c4ee6bef4a · report fixture: signature weights:str/0/str · returned int · level recorded 2026-09-24
tv_loss in 17 papers losses.py ran MIT (permissive) · bd81f2c248f04da7 · report fixture: signature x:Tensor/4/float, beta:float/0/float, reg_coeff:int/0/int · returned Tensor · level recorded 2026-09-24
window_partition in 377 papers
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
model.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · c4b5a8b25f271a68 · report fixture: signature x:Tensor/4/float, win_size:int/0/int, dilation_rate:int/0/int · returned Tensor · level recorded 2026-09-22
window_reverse in 296 papers model.py ran · our draft was wrong MIT (permissive) · e2cf4a766e987768 · report fixture: signature windows:Tensor/4/float, win_size:int/0/int, H:int/0/int, W:int/0/int, dilation_rate:int/0/int · returned Tensor · level recorded 2026-09-22
BaseModel in 92 papers model.py unverified MIT (permissive) · 5542fb90957b9612 · report
BasicBaseModelLayer model.py unverified MIT (permissive) · 1d8e36a85946250f · report
BasicTransformerBlock in 22 papers model.py unverified MIT (permissive) · 6cadca82908e051f · report
NewFusion model.py unverified MIT (permissive) · bfa8ccef51294b6d · report
OutputProj_HWC model.py unverified MIT (permissive) · 2c8aebefe85a9e02 · report
WindowAttention in 50 papers model.py unverified MIT (permissive) · b9d721c692df1a80 · report
load_optim utils/model_utils.py unverified MIT (permissive) · 81e30648b66c8cf7 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for FBAnet (graph method: FBAnet). 26 bricks; individually on a fixture: 19 ran (of which 15 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.

  1. BaseModel entry · level 0 · unverified · 5542fb90957b9612
  2. BasicBaseModelLayer model · level 0 · unverified · 1d8e36a85946250f
  3. Downsample model · level 1 · ran · 5b78062820f7c165
  4. InputProj model · level 1 · ran · 3a9a8599d8e3c1d2
  5. NewFusion model · level 0 · unverified · bfa8ccef51294b6d
  6. OutputProj model · level 0 · unverified · d725a09f8ee42746
  7. OutputProj_HWC helper · level 0 · unverified · 2c8aebefe85a9e02
  8. ResBlock helper · level 1 · ran · b72b66e9ec7fe38f
  9. SEBasicBlock helper · level 1 · ran · 01718b15b1a6769a
  10. Upsample model · level 1 · ran · 93f3d523e11ee887
  11. Upsampler helper · level 1 · ran · 71266d282079ed33
  12. default_conv helper · level 1 · ran · our draft was wrong · 8b0e794d4d8f9b13
  13. BasicTransformerBlock model · level 0 · unverified · 6cadca82908e051f
  14. Downsample_flatten helper · level 1 · ran · 323265751addf553
  15. Upsample_flatten helper · level 1 · ran · a1f6b98b451f9950
  16. SELayer helper · level 1 · ran · 67adfee5b5d01e0c
  17. conv3x3 helper · level 1 · ran · our draft was wrong · 583f9780bdd00a45
  18. LeFF model · level 1 · ran · 77ff7b6704558111
  19. Mlp model · level 1 · ran · 6048703a72836ea7
  20. WindowAttention model · level 0 · unverified · b9d721c692df1a80
  21. window_partition helper · level 1 · ran; the contract check could not run (RAISES) · c4b5a8b25f271a68
  22. window_reverse helper · level 1 · ran · our draft was wrong · e2cf4a766e987768
  23. ConvProjection helper · level 1 · ran · ac174fec3e23aa7b
  24. LinearProjection helper · level 1 · ran · 8cc07c7cf8e3296d
  25. LinearProjection_Concat_kv helper · level 1 · ran · a88d832a42153fba
  26. SepConv2d helper · level 1 · ran · 3cfb6d8134fa5a62

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2309.04803") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Burst Image Super-ResolutionImage Super-ResolutionSuper-Resolution

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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