Papers › Residual Dense Network for Image Super-Resolution

Residual Dense Network for Image Super-Resolution

24 Feb 2018CVPR 2018 6arXiv:1802.08797archive 2025-07-28

Yulun Zhang, Yapeng Tian, Yu Kong, Bineng Zhong, Yun Fu

A very deep convolutional neural network (CNN) has recently achieved great success for image super-resolution (SR) and offered hierarchical features as well. However, most deep CNN based SR models do not make full use of the hierarchical features from the original low-resolution (LR) images, thereby achieving relatively-low performance. In this paper, we propose a novel residual dense network (RDN) to address this problem in image SR. We fully exploit the hierarchical features from all the convolutional layers. Specifically, we propose residual dense block (RDB) to extract abundant local features via dense connected convolutional layers. RDB further allows direct connections from the state of preceding RDB to all the layers of current RDB, leading to a contiguous memory (CM) mechanism. Local feature fusion in RDB is then used to adaptively learn more effective features from preceding and current local features and stabilizes the training of wider network. After fully obtaining dense local features, we use global feature fusion to jointly and adaptively learn global hierarchical features in a holistic way. Extensive experiments on benchmark datasets with different degradation models show that our RDN achieves favorable performance against state-of-the-art methods.

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="1802.08797")

Code

Syntology Ran 7 of 24 code samples harvested from 4 repositories linked to this paper; 17 have no recorded run. Of those that ran: 2 ran · honoured contract; 5 ran · our draft was wrong.

By repository: community (archive-listed): 23 samples from 4 repositories, 6 ran; 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

16 repositories listed; official and paper-mentioned ones first.

yulunzhang/RDN officialmentioned in papermentioned on GitHubpytorch report
DivJAth/DeepLearning5922 mentioned on GitHubMIT report
coloquinte/torchsr mentioned on GitHubpytorch report
idealo/image-super-resolution mentioned on GitHubtf report
keerthan2/RDN-Tensorflow mentioned on GitHubtf report
proteus1991/GridDehazeNet mentioned on GitHubpytorch report
puffnjackie/pytorch-super-resolution-implementations mentioned on GitHubpytorchBSD-3-Clause report
yjn870/rdn-pytorch mentioned 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

24 samples harvested; 7 ran; 2 honoured the contract we drafted; 17 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.

2ran · honoured contract
5ran · our draft was wrong
17unverified

Licence: 1 of the 24 samples is 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 4 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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.

cset DivJAth/DeepLearning5922/WorkerServer/progressive_gans/networks.py community (archive-listed) ran · our draft was wrong MIT (permissive) · f7d82b02ff7c7fe1 · report
lerp DivJAth/DeepLearning5922/WorkerServer/progressive_gans/networks.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · 0c45399f3741921e · report
lerp_clip DivJAth/DeepLearning5922/WorkerServer/progressive_gans/networks.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · 6e81789f8f2068c8 · report
rdn coloquinte/torchsr/torchsr/models/rdn.py community (archive-listed) ran · our draft was wrong MIT (permissive) · cfb719de8e4309a5 · report
rdn_a coloquinte/torchsr/torchsr/models/rdn.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 8b6862fabd89b5b7 · report
rdn_b coloquinte/torchsr/torchsr/models/rdn.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 325673b8c71b9a93 · report
G_wgan_acgan DivJAth/DeepLearning5922/WorkerServer/progressive_gans/loss.py community (archive-listed) unverified MIT (permissive) · 82992ce1f4764e7b · report
calculate_valid_crop_size puffnjackie/pytorch-super-resolution-implementations/utils.py community (archive-listed) unverified BSD-3-Clause (permissive) · c889b417f65ffc2a · report
convert_rgb_to_y yjn870/rdn-pytorch/utils.py community (archive-listed) unverified MIT (permissive) · 7dfb710bae9177e3 · report
denormalize yjn870/rdn-pytorch/utils.py community (archive-listed) unverified MIT (permissive) · 1147a2dbb2f252eb · report
getImageArr DivJAth/DeepLearning5922/WorkerServer/FCN8/fcn8Inference.py community (archive-listed) unverified MIT (permissive) · 62ec85e3d3a6e20b · report
getImageArr DivJAth/DeepLearning5922/WorkerServer/FCN8/temp.py community (archive-listed) unverified MIT (permissive) · 93fe2690eaf6ae65 · report
getImageArr DivJAth/DeepLearning5922/WorkerServer/FCN8/vgg16part2.py community (archive-listed) unverified MIT (permissive) · 08e9f90b6fa9aaed · report
getSegmentationArr DivJAth/DeepLearning5922/WorkerServer/FCN8/vgg16part2.py community (archive-listed) unverified MIT (permissive) · 390a59999fa7e133 · report
input_transform puffnjackie/pytorch-super-resolution-implementations/utils.py community (archive-listed) unverified BSD-3-Clause (permissive) · b149efda3d8e6d7d · report
is_image_file puffnjackie/pytorch-super-resolution-implementations/dataset.py community (archive-listed) unverified BSD-3-Clause (permissive) · 0516d5020cce56da · report
load_RGB_img puffnjackie/pytorch-super-resolution-implementations/dataset.py community (archive-listed) unverified BSD-3-Clause (permissive) · fc54dc3ed3050dee · report
load_img puffnjackie/pytorch-super-resolution-implementations/dataset.py community (archive-listed) unverified BSD-3-Clause (permissive) · 283c3f29d71d3276 · report
load_imgs_from_path DivJAth/DeepLearning5922/WebServer/utils.py community (archive-listed) unverified MIT (permissive) · 7e3fea997fd296f8 · report
normalize_images DivJAth/DeepLearning5922/dummy_client.py community (archive-listed) unverified MIT (permissive) · 7b611f1478dce021 · report
preprocess yjn870/rdn-pytorch/utils.py community (archive-listed) unverified MIT (permissive) · df34751a7f8082d3 · report
save_imgs_to_path DivJAth/DeepLearning5922/WebServer/utils.py community (archive-listed) unverified MIT (permissive) · b83ca28b09fb0076 · report
target_transform puffnjackie/pytorch-super-resolution-implementations/utils.py community (archive-listed) unverified BSD-3-Clause (permissive) · 02cc7a7cfd24376d · report
get_network identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · 9bd62e7608b51355 · report

Tasks

Color Image DenoisingImage Super-ResolutionSuper-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Color Image Denoising CBSD68 sigma50 Residual Dense Network + PSNR 28.34 #7 of 18 Archive leaderboard report
Image Super-Resolution BSD100 - 4x upscaling RDN PSNR 27.72 #25 of 71 Archive leaderboard report
Image Super-Resolution BSD100 - 4x upscaling RDN SSIM 0.7419 #25 of 71 Archive leaderboard report
Image Super-Resolution IXI RDN PSNR 2x T2w 38.75 #5 of 9 Archive leaderboard report
Image Super-Resolution IXI RDN PSNR 4x T2w 31.45 #5 of 9 Archive leaderboard report
Image Super-Resolution IXI RDN SSIM 4x T2w 0.9324 #5 of 9 Archive leaderboard report
Image Super-Resolution IXI RDN SSIM for 2x T2w 0.9838 #5 of 9 Archive leaderboard report
Image Super-Resolution Manga109 - 4x upscaling RDN PSNR 31.0 #34 of 50 Archive leaderboard report
Image Super-Resolution Manga109 - 4x upscaling RDN SSIM 0.9151 #34 of 50 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling RDN PSNR 28.81 #47 of 104 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling RDN SSIM 0.7871 #47 of 104 Archive leaderboard report
Image Super-Resolution Urban100 - 4x upscaling RDN PSNR 26.61 #33 of 65 Archive leaderboard report
Image Super-Resolution Urban100 - 4x upscaling RDN SSIM 0.8028 #33 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.

Methods

Batch NormalizationConcatenated Skip ConnectionConvolutionDense BlockReLU

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