Papers › Feedback Network for Image Super-Resolution

Feedback Network for Image Super-Resolution

23 Mar 2019CVPR 2019 6arXiv:1903.09814archive 2025-07-28

Zhen Li, Jinglei Yang, Zheng Liu, Xiaomin Yang, Gwanggil Jeon, Wei Wu

Recent advances in image super-resolution (SR) explored the power of deep learning to achieve a better reconstruction performance. However, the feedback mechanism, which commonly exists in human visual system, has not been fully exploited in existing deep learning based image SR methods. In this paper, we propose an image super-resolution feedback network (SRFBN) to refine low-level representations with high-level information. Specifically, we use hidden states in an RNN with constraints to achieve such feedback manner. A feedback block is designed to handle the feedback connections and to generate powerful high-level representations. The proposed SRFBN comes with a strong early reconstruction ability and can create the final high-resolution image step by step. In addition, we introduce a curriculum learning strategy to make the network well suitable for more complicated tasks, where the low-resolution images are corrupted by multiple types of degradation. Extensive experimental results demonstrate the superiority of the proposed SRFBN in comparison with the state-of-the-art methods. Code is avaliable at https://github.com/Paper99/SRFBN_CVPR19.

PaperPDFConference PDFCodeCode 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 7 code samples harvested from 1 repository linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 1 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: 7 samples from 1 repository, 7 ran (5 with no instrument failure; 2 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

Paper99/SRFBN_CVPR19 officialmentioned in papermentioned on GitHubpytorchMITSyntology: 7 samples, 7 ran (2 instrument-failed) · 0 unverified report
JihyunLee9805/GMFN mentioned on GitHubpytorchSyntology: not harvested report
tianbaochou/YOUKU-VSRE-2019-49th mentioned on GitHubpytorchSyntology: not harvested report
turboLIU/SRFBN-tensorflow mentioned on GitHubtfSyntology: 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.

Code Syntology ran Syntology

7 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 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 · our draft was wrong
1ran; the contract check could not run
5ran

Licence: 0 of the 7 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 Paper99/SRFBN_CVPR19. “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.

Paper99/SRFBN_CVPR19 official repository 7 samples, 7 ran (2 instrument-failed) · 0 unverified
Tensor2np utils/util.py ran MIT (permissive) · 35b603c1f100d4a3 · report fixture: signature tensor_list:list/1/Tensor, rgb_range:float/0/float · returned list · level recorded 2026-09-25
activation in 30 papers networks/blocks.py ran MIT (permissive) · c2c7f6f8109d22e1 · report fixture: signature act_type:str/0/str, inplace:bool/0/bool, slope:float/0/float, n_prelu:int/0/int · returned ReLU · level recorded 2026-09-25
default_conv in 70 papers networks/edsr_arch.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
norm in 120 papers
census: 23 implementations from 26 papers, 15 distinct outputs across 6 buckets, one shared input per bucket
networks/blocks.py ran MIT (permissive) · eb98b2d07e298ab0 · report fixture: signature n_feature:int/0/int, norm_type:str/0/str · returned BatchNorm2d · level recorded 2026-09-25
pad in 85 papers networks/blocks.py ran MIT (permissive) · 5c81afc612dd8e12 · report fixture: signature pad_type:str/0/str, padding:int/0/int · returned ReflectionPad2d · level recorded 2026-09-25
rgb2ycbcr in 16 papers utils/util.py ran; the contract check could not run (RAISES) MIT (permissive) · 2b1245dfa8d76fe2 · report fixture: signature img:ndarray/3/int, only_y:bool/0/bool · returned ndarray · level recorded 2026-09-24
ycbcr2rgb in 8 papers utils/util.py ran fingerprinted MIT (permissive) · 9f036ed5398a4dfd · report fixture: signature img:ndarray/3/int · returned ndarray · level recorded 2026-09-25

Tasks

Image Super-ResolutionSuper-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Super-Resolution BSD100 - 2x upscaling SRFBN PSNR 32.29 #20 of 30 Archive leaderboard report
Image Super-Resolution BSD100 - 3x upscaling SRFBN PSNR 29.24 #14 of 21 Archive leaderboard report
Image Super-Resolution BSD100 - 4x upscaling SRFBN PSNR 27.72 #26 of 71 Archive leaderboard report
Image Super-Resolution BSD100 - 4x upscaling SRFBN SSIM 0.7409 #26 of 71 Archive leaderboard report
Image Super-Resolution FFHQ 1024 x 1024 - 4x upscaling SRFBN FID 17.14 #4 of 9 Archive leaderboard report
Image Super-Resolution FFHQ 1024 x 1024 - 4x upscaling SRFBN MS-SSIM 0.931 #4 of 9 Archive leaderboard report
Image Super-Resolution FFHQ 1024 x 1024 - 4x upscaling SRFBN PSNR 27.90 #4 of 9 Archive leaderboard report
Image Super-Resolution FFHQ 1024 x 1024 - 4x upscaling SRFBN SSIM 0.822 #4 of 9 Archive leaderboard report
Image Super-Resolution FFHQ 256 x 256 - 4x upscaling SRFBN FID 132.59 #5 of 11 Archive leaderboard report
Image Super-Resolution FFHQ 256 x 256 - 4x upscaling SRFBN MS-SSIM 0.895 #5 of 11 Archive leaderboard report
Image Super-Resolution FFHQ 256 x 256 - 4x upscaling SRFBN PSNR 21.96 #5 of 11 Archive leaderboard report
Image Super-Resolution FFHQ 256 x 256 - 4x upscaling SRFBN SSIM 0.693 #5 of 11 Archive leaderboard report
Image Super-Resolution FFHQ 512 x 512 - 4x upscaling SRFBN FED 0.0984 #4 of 8 Archive leaderboard report
Image Super-Resolution FFHQ 512 x 512 - 4x upscaling SRFBN FID 20.032 #4 of 8 Archive leaderboard report
Image Super-Resolution FFHQ 512 x 512 - 4x upscaling SRFBN LLE 2.066 #4 of 8 Archive leaderboard report
Image Super-Resolution FFHQ 512 x 512 - 4x upscaling SRFBN LPIPS 0.2406 #4 of 8 Archive leaderboard report
Image Super-Resolution FFHQ 512 x 512 - 4x upscaling SRFBN MS-SSIM 0.953 #4 of 8 Archive leaderboard report
Image Super-Resolution FFHQ 512 x 512 - 4x upscaling SRFBN NIQE 13.901 #4 of 8 Archive leaderboard report
Image Super-Resolution FFHQ 512 x 512 - 4x upscaling SRFBN PSNR 29.577 #4 of 8 Archive leaderboard report
Image Super-Resolution FFHQ 512 x 512 - 4x upscaling SRFBN SSIM 0.827 #4 of 8 Archive leaderboard report
Image Super-Resolution Manga109 - 2x upscaling SRFBN PSNR 39.08 #19 of 21 Archive leaderboard report
Image Super-Resolution Manga109 - 3x upscaling SRFBN PSNR 34.18 #14 of 17 Archive leaderboard report
Image Super-Resolution Manga109 - 4x upscaling SRFBN PSNR 31.15 #33 of 50 Archive leaderboard report
Image Super-Resolution Manga109 - 4x upscaling SRFBN SSIM 0.9160 #33 of 50 Archive leaderboard report
Image Super-Resolution Set14 - 2x upscaling SRFBN PSNR 33.82 #19 of 35 Archive leaderboard report
Image Super-Resolution Set14 - 3x upscaling SRFBN PSNR 30.1 #19 of 24 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling SRFBN PSNR 28.81 #48 of 104 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling SRFBN SSIM 0.7868 #48 of 104 Archive leaderboard report
Image Super-Resolution Set5 - 2x upscaling SRFBN PSNR 38.11 #24 of 41 Archive leaderboard report
Image Super-Resolution Set5 - 3x upscaling SRFBN PSNR 34.70 #18 of 32 Archive leaderboard report
Image Super-Resolution Urban100 - 2x upscaling SRFBN PSNR 32.62 #22 of 29 Archive leaderboard report
Image Super-Resolution Urban100 - 3x upscaling SRFBN PSNR 28.73 #18 of 22 Archive leaderboard report
Image Super-Resolution Urban100 - 4x upscaling SRFBN PSNR 26.6 #35 of 65 Archive leaderboard report
Image Super-Resolution Urban100 - 4x upscaling SRFBN SSIM 0.8015 #35 of 65 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