Papers › Accelerating the Super-Resolution Convolutional Neural Network

Accelerating the Super-Resolution Convolutional Neural Network

1 Aug 2016arXiv:1608.00367archive 2025-07-28

Chao Dong, Chen Change Loy, Xiaoou Tang

As a successful deep model applied in image super-resolution (SR), the Super-Resolution Convolutional Neural Network (SRCNN) has demonstrated superior performance to the previous hand-crafted models either in speed and restoration quality. However, the high computational cost still hinders it from practical usage that demands real-time performance (24 fps). In this paper, we aim at accelerating the current SRCNN, and propose a compact hourglass-shape CNN structure for faster and better SR. We re-design the SRCNN structure mainly in three aspects. First, we introduce a deconvolution layer at the end of the network, then the mapping is learned directly from the original low-resolution image (without interpolation) to the high-resolution one. Second, we reformulate the mapping layer by shrinking the input feature dimension before mapping and expanding back afterwards. Third, we adopt smaller filter sizes but more mapping layers. The proposed model achieves a speed up of more than 40 times with even superior restoration quality. Further, we present the parameter settings that can achieve real-time performance on a generic CPU while still maintaining good performance. A corresponding transfer strategy is also proposed for fast training and testing across different upscaling factors.

PaperPDFCodeCode 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 15 code samples harvested from 4 repositories linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 15 samples from 4 repositories, 14 ran (14 with no instrument failure; 0 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 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

Araxeus/PNG-Upscale mentioned on GitHubtfMITSyntology: not harvested report
GatorSense/SRrootimaging mentioned on GitHubpytorchSyntology: not harvested report
Lornatang/FSRCNN-PyTorch mentioned on GitHubpytorchApache-2.0Syntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
MaxHolmberg96/Fast-super-resolution-by-CNN mentioned on GitHubtfMITSyntology: 5 samples, 5 ran (0 instrument-failed) · 0 unverified report
MohammedAlkhrashi/4D-Dream mentioned on GitHubSyntology: not harvested report
MohammedAlkhrashi/TMA mentioned on GitHubSyntology: not harvested report
Nhat-Thanh/FSRCNN-Pytorch mentioned on GitHubpytorchMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
Nhat-Thanh/FSRCNN-TF mentioned on GitHubtfMITSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
NicoCeresa/FSRCNN-2016 mentioned on GitHubpytorchSyntology: not harvested report
OlgaChernytska/Super-Resolution-with-FSRCNN mentioned on GitHubtfSyntology: not harvested report
Zorrat/Image-Denoiser-Supersampling-and-Editor mentioned on GitHubSyntology: not harvested report
amiq-consulting/image-upscaling-CNN mentioned on GitHubNOASSERTIONSyntology: not harvested report
poikilos/pyrotocanvas mentioned on GitHubtfGPL-3.0Syntology: not harvested report
xanderex-sid/FSRCNN mentioned on GitHubpytorchSyntology: not harvested report
yjn870/FSRCNN-pytorch mentioned on GitHubpytorchSyntology: not harvested report
MindSpore-scientific-2/code-11 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to LLMs as Zero-shot Graph Learners: Alignment of GNN Representations with LLM Token Embeddings (arXiv:2408.14512; that paper's own run record: 9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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

15 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

14ran
1unverified

Licence: 0 of the 15 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 4 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.

Lornatang/FSRCNN-PyTorch community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
cubic in 19 papers imgproc.py ran fingerprinted Apache-2.0 (permissive) · 0d462506dbb0db2d · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-26
image2tensor in 6 papers imgproc.py ran Apache-2.0 (permissive) · 4579f4a0e343f30e · report fixture: signature image:ndarray/3/float, range_norm:bool/0/bool, half:bool/0/bool · returned Tensor · level recorded 2026-09-26
tensor2image in 10 papers imgproc.py ran Apache-2.0 (permissive) · bc562954fab9c9fb · report fixture: signature tensor:Tensor/4/float, range_norm:bool/0/bool, half:bool/0/bool · returned ndarray · level recorded 2026-09-24
MaxHolmberg96/Fast-super-resolution-by-CNN community (archive-listed) 5 samples, 5 ran (0 instrument-failed) · 0 unverified
FSRCNN fsrcnn.py ran MIT (permissive) · dd97234bcfdf3615 · report fixture: signature d:int/0/int, s:int/0/int, m:int/0/int, upscaling:int/0/int · returned Sequential · level recorded 2026-09-26
convert_rgb_to_y data.py ran MIT (permissive) · 7dfb710bae9177e3 · report fixture: signature img:Tensor/3/float, dim_order:str/0/str · returned Tensor · level recorded 2026-09-26
convert_rgb_to_ycbcr data.py ran fingerprinted MIT (permissive) · e0dcb85fc7cb24b0 · report fixture: signature img:ndarray/3/float, dim_order:str/0/str · returned ndarray · level recorded 2026-09-26
convert_ycbcr_to_rgb data.py ran fingerprinted MIT (permissive) · 3e396b602fde8231 · report fixture: signature img:ndarray/3/float, dim_order:str/0/str · returned ndarray · level recorded 2026-09-26
psnr in 88 papers
census: 9 implementations from 11 papers, 6 distinct outputs across 4 buckets, one shared input per bucket
fsrcnn.py ran MIT (permissive) · df6069cdd75250cc · report fixture: signature y_pred:EagerTensor/4/float, y_true:EagerTensor/4/float, clip:bool/0/bool · returned EagerTensor · level recorded 2026-09-26
Nhat-Thanh/FSRCNN-Pytorch community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
read_image in 73 papers utils/common.py ran MIT (permissive) · 4d448d32e15f04c9 · report fixture: signature filepath:str/0/str · returned Tensor · level recorded 2026-09-26
rgb2ycbcr in 16 papers utils/common.py ran MIT (permissive) · d8058eded6a9e999 · report fixture: signature src:Tensor/3/float · returned Tensor · level recorded 2026-09-26
ycbcr2rgb in 8 papers utils/common.py ran MIT (permissive) · ef42ea280e97a9f8 · report fixture: signature src:Tensor/3/float · returned Tensor · level recorded 2026-09-26
Nhat-Thanh/FSRCNN-TF community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
read_image in 73 papers utils/common.py ran MIT (permissive) · 05f12c47fb9b8978 · report fixture: signature filepath:str/0/str · returned EagerTensor · level recorded 2026-09-26
rgb2ycbcr in 16 papers utils/common.py ran MIT (permissive) · 3760ee509acdf19f · report fixture: signature src:ndarray/3/int · returned EagerTensor · level recorded 2026-09-26
ycbcr2rgb in 8 papers utils/common.py ran MIT (permissive) · 3b0edbcfb724a432 · report fixture: signature src:ndarray/3/float · returned EagerTensor · level recorded 2026-09-26
FSRCNN neuralnet.py unverified MIT (permissive) · 9380592364aafe4f · report

Tasks

Image Super-ResolutionSuper-Resolution

1 archive task tag without a task page not shown.

Datasets

Introduced by this paper, per the archive.

General-100

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Super-Resolution BSD100 - 2x upscaling FSRCNN [[Dong et al.2016]] PSNR 31.53 #30 of 30 Archive leaderboard report
Image Super-Resolution FFHQ 1024 x 1024 - 4x upscaling FSRCNN FID 23.97 #6 of 9 Archive leaderboard report
Image Super-Resolution FFHQ 1024 x 1024 - 4x upscaling FSRCNN MS-SSIM 0.951 #6 of 9 Archive leaderboard report
Image Super-Resolution FFHQ 1024 x 1024 - 4x upscaling FSRCNN PSNR 24.71 #6 of 9 Archive leaderboard report
Image Super-Resolution FFHQ 1024 x 1024 - 4x upscaling FSRCNN SSIM 0.804 #6 of 9 Archive leaderboard report
Image Super-Resolution FFHQ 256 x 256 - 4x upscaling FSRCNN FID 139.78 #6 of 11 Archive leaderboard report
Image Super-Resolution FFHQ 256 x 256 - 4x upscaling FSRCNN MS-SSIM 0.930 #6 of 11 Archive leaderboard report
Image Super-Resolution FFHQ 256 x 256 - 4x upscaling FSRCNN PSNR 22.45 #6 of 11 Archive leaderboard report
Image Super-Resolution FFHQ 256 x 256 - 4x upscaling FSRCNN SSIM 0.709 #6 of 11 Archive leaderboard report
Image Super-Resolution Manga109 - 4x upscaling FSRCNN PSNR 27.90 #44 of 50 Archive leaderboard report
Image Super-Resolution Manga109 - 4x upscaling FSRCNN SSIM 0.8610 #44 of 50 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

SPEED

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