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 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="1903.09814")

Code

Syntology Ran 2 of 7 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 1 ran with no contract checked.

By repository: official repository: 7 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Paper99/SRFBN_CVPR19 officialmentioned in papermentioned on GitHubpytorchMIT report
JihyunLee9805/GMFN mentioned on GitHubpytorch report
tianbaochou/YOUKU-VSRE-2019-49th mentioned on GitHubpytorch report
turboLIU/SRFBN-tensorflow mentioned on GitHubtf 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; 2 ran; 0 honoured the contract we drafted; 5 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 · our draft was wrong
1ran
5unverified

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. “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.

default_conv Paper99/SRFBN_CVPR19/networks/edsr_arch.py official repository ran · our draft was wrong MIT (permissive) · 8b0e794d4d8f9b13 · report
rgb2ycbcr Paper99/SRFBN_CVPR19/utils/util.py official repository ran MIT (permissive) · 2b1245dfa8d76fe2 · report
Tensor2np Paper99/SRFBN_CVPR19/utils/util.py official repository unverified MIT (permissive) · 35b603c1f100d4a3 · report
activation Paper99/SRFBN_CVPR19/networks/blocks.py official repository unverified MIT (permissive) · c2c7f6f8109d22e1 · report
norm Paper99/SRFBN_CVPR19/networks/blocks.py official repository unverified MIT (permissive) · eb98b2d07e298ab0 · report
pad Paper99/SRFBN_CVPR19/networks/blocks.py official repository unverified MIT (permissive) · 5c81afc612dd8e12 · report
ycbcr2rgb Paper99/SRFBN_CVPR19/utils/util.py official repository unverified MIT (permissive) · 9f036ed5398a4dfd · report

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