Papers › Deep Back-Projection Networks For Super-Resolution

Deep Back-Projection Networks For Super-Resolution

7 Mar 2018CVPR 2018 6arXiv:1803.02735archive 2025-07-28

Muhammad Haris, Greg Shakhnarovich, Norimichi Ukita

The feed-forward architectures of recently proposed deep super-resolution networks learn representations of low-resolution inputs, and the non-linear mapping from those to high-resolution output. However, this approach does not fully address the mutual dependencies of low- and high-resolution images. We propose Deep Back-Projection Networks (DBPN), that exploit iterative up- and down-sampling layers, providing an error feedback mechanism for projection errors at each stage. We construct mutually-connected up- and down-sampling stages each of which represents different types of image degradation and high-resolution components. We show that extending this idea to allow concatenation of features across up- and down-sampling stages (Dense DBPN) allows us to reconstruct further improve super-resolution, yielding superior results and in particular establishing new state of the art results for large scaling factors such as 8x across multiple data sets.

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 14 code samples harvested from 3 repositories linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 14 samples from 3 repositories, 14 ran (12 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 14 samples that ran has no recorded date.

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

15517965908/keras-DBPN mentioned on GitHubtfSyntology: not harvested report
LEEPEIQIN/EDSR mentioned on GitHubpytorchMITSyntology: 5 samples, 5 ran (2 instrument-failed) · 0 unverified report
LWChen20/RCAN mentioned on GitHubpytorchMITSyntology: not harvested report
SimoneDutto/EDSR mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Improved Training of Wasserstein GANs (arXiv:1704.00028; that paper's own run record: 27 ran (of which 10 constructed an object rather than computing a result; 19 with no instrument failure: 1 honoured, 0 violated, 18 with no contract checked; 8 where Syntology's instrument failed) · 22 unverified); nothing checks that they implement this paper's method. report
akashpalrecha/deblurring-pipeline mentioned on GitHubpytorchMITSyntology: not harvested report
akashpalrecha/superres-deformable mentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
laowng/GISR mentioned on GitHubpytorchMITSyntology: not harvested report
markmaxt/VideoSR mentioned on GitHubpytorchMITSyntology: not harvested report
rajatthepagal/DBPN-Keras mentioned on GitHubtfSyntology: not harvested report
rkem1542/EDSR-pytorch mentioned on GitHubpytorchMITSyntology: not harvested report
sanghyun-son/EDSR-PyTorch mentioned on GitHubpytorchMITSyntology: not harvested report
thstkdgus35/EDSR-PyTorch mentioned on GitHubpytorchMITSyntology: not harvested report
tinnunculus/Denoising_SR mentioned on GitHubtfSyntology: not harvested report
zhusiling/EDSR mentioned on GitHubpytorchMITSyntology: not harvested report
2023-MindSpore-1/ms-code-210 mindsporeSyntology: not harvested report
alterzero/DBPN-Pytorch pytorchMITSyntology: 8 samples, 8 ran (0 instrument-failed) · 0 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

14 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 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 · violated contract
2ran · our draft was wrong
11ran

Licence: 4 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 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 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

LEEPEIQIN/EDSR community (archive-listed) 5 samples, 5 ran (2 instrument-failed) · 0 unverified
calc_psnr in 26 papers src/utility.py ran MIT (permissive) here; the stored copy is pointer only · d4592ac83c04a5fd · report fixture: signature sr:Tensor/4/float, hr:Tensor/4/float, scale:int/0/int, rgb_range:int/0/int, dataset:DummyDatasetWrapper/0/? · returned float · level recorded 2026-09-24
default_conv in 70 papers src/model/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
make_optimizer in 32 papers src/utility.py ran MIT (permissive) · 5eed111fb0fb051b · report fixture: signature args:ArgsConfig/0/?, target:callable/0/? · returned CustomOptimizer · level recorded 2026-09-24
projection_conv src/model/ddbpn.py ran MIT (permissive) · 3cadb1fed3be1893 · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, scale:int/0/int, up:bool/0/bool · returned ConvTranspose2d · level recorded 2026-09-25
quantize in 70 papers
census: 8 implementations from 11 papers, 6 distinct outputs across 3 buckets, one shared input per bucket
src/utility.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · b1c1acd3c89a39f3 · report fixture: signature img:Tensor/2/float, rgb_range:float/0/float · returned Tensor · level recorded 2026-09-24
akashpalrecha/superres-deformable community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
gated_conv src/model/cgc_edsr.py ran MIT (permissive) · b70e2f411ef9239a · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, kernel_size:int/0/int, bias:bool/0/bool · returned CGConv2d · level recorded 2026-09-26
alterzero/DBPN-Pytorch community (archive-listed) 8 samples, 8 ran (0 instrument-failed) · 0 unverified
denorm in 23 papers utils.py ran fingerprinted MIT (permissive) · 754eaaec87e45177 · report fixture: signature img:Tensor/4/float, vgg:bool/0/bool · returned Tensor · level recorded 2026-09-26
gram_matrix in 45 papers
census: 7 implementations from 9 papers, 4 distinct outputs on one shared input
utils.py ran fingerprinted MIT (permissive) · 4be7bb2418de3fb9 · report fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-26
is_image_file in 157 papers dataset.py ran MIT (permissive) · 0516d5020cce56da · report fixture: signature filename:str/0/str · returned bool · level recorded 2026-09-25
load_img in 47 papers dataset.py ran MIT (permissive) here; the stored copy is pointer only · 27ebc73345cd00a0 · report fixture: signature filepath:str/0/str · returned Image · level recorded 2026-09-24
norm in 120 papers
census: 23 implementations from 26 papers, 15 distinct outputs across 6 buckets, one shared input per bucket
utils.py ran fingerprinted MIT (permissive) · 5178867afe8613af · report fixture: signature img:Tensor/4/float, vgg:bool/0/bool · returned Tensor · level recorded 2026-09-26
rescale_img dataset.py ran MIT (permissive) here; the stored copy is pointer only · 25678766a66c3ac4 · report fixture: signature img_in:Image/0/?, scale:float/0/float · returned Image · level recorded 2026-09-24
str2bool in 533 papers eval_gan.py ran · violated contract MIT (permissive) · 25c7475539e39da4 · report fixture: signature v:str/0/str · returned bool · level recorded, date not recorded
x8_forward eval_gan.py ran MIT (permissive) · 007d490d5ea4d153 · report fixture: signature img:Tensor/4/float, model:callable/0/?, precision:str/0/str · returned Tensor · level recorded 2026-09-26

Tasks

Image Super-ResolutionSuper-ResolutionVideo Super-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Super-Resolution BSD100 - 4x upscaling D-DBPN PSNR 27.72 #27 of 71 Archive leaderboard report
Image Super-Resolution BSD100 - 4x upscaling D-DBPN SSIM 0.740 #27 of 71 Archive leaderboard report
Image Super-Resolution Manga109 - 4x upscaling D-DBPN SSIM 0.914 #37 of 50 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling D-DBPN PSNR 28.82 #46 of 104 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling D-DBPN SSIM 0.786 #46 of 104 Archive leaderboard report
Image Super-Resolution Urban100 - 4x upscaling D-DBPN SSIM 0.795 #64 of 65 Archive leaderboard report
Video Super-Resolution Vid4 - 4x upscaling DBPN PSNR 25.37 #21 of 27 Archive leaderboard report
Video Super-Resolution Vid4 - 4x upscaling DBPN SSIM 0.737 #21 of 27 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