Papers › Deep Constrained Least Squares for Blind Image Super-Resolution

Deep Constrained Least Squares for Blind Image Super-Resolution

15 Feb 2022CVPR 2022 1arXiv:2202.07508archive 2025-07-28

Ziwei Luo, Haibin Huang, Lei Yu, Youwei Li, Haoqiang Fan, Shuaicheng Liu

In this paper, we tackle the problem of blind image super-resolution(SR) with a reformulated degradation model and two novel modules. Following the common practices of blind SR, our method proposes to improve both the kernel estimation as well as the kernel-based high-resolution image restoration. To be more specific, we first reformulate the degradation model such that the deblurring kernel estimation can be transferred into the low-resolution space. On top of this, we introduce a dynamic deep linear filter module. Instead of learning a fixed kernel for all images, it can adaptively generate deblurring kernel weights conditional on the input and yield a more robust kernel estimation. Subsequently, a deep constrained least square filtering module is applied to generate clean features based on the reformulation and estimated kernel. The deblurred feature and the low input image feature are then fed into a dual-path structured SR network and restore the final high-resolution result. To evaluate our method, we further conduct evaluations on several benchmarks, including Gaussian8 and DIV2KRK. Our experiments demonstrate that the proposed method achieves better accuracy and visual improvements against state-of-the-art methods.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 6 code samples harvested from 1 repository linked to this paper: 0 ran · 6 unverified.

By repository: official repository: 6 samples from 1 repository, 0 ran (0 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.

megvii-research/dcls-sr officialmentioned in papermentioned on GitHubpytorchSyntology: 6 samples, 0 ran · 6 unverified report
algolzw/dcls mentioned in papermentioned on GitHubMITSyntology: 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

6 samples harvested: 0 ran · 6 unverified. 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.

6unverified

Licence: 0 of the 6 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 megvii-research/dcls-sr. “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 “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.

megvii-research/dcls-sr official repository 6 samples, 0 ran · 6 unverified
CLS codes/config/DCLS/models/modules/dcls_arch.py unverified MIT (permissive) · 99aa6966a166e993 · report
DCLS codes/config/DCLS/models/modules/dcls_arch.py unverified MIT (permissive) · 33653a69fe625918 · report
DPCAB codes/config/DCLS/models/modules/dcls_arch.py unverified MIT (permissive) · 6d17723c7dd847a6 · report
DPCAG codes/config/DCLS/models/modules/dcls_arch.py unverified MIT (permissive) · 07a1c6d96c7e56c1 · report
Estimator in 7 papers codes/config/DCLS/models/modules/dcls_arch.py unverified MIT (permissive) · 8fa6861f618410ad · report
Restorer codes/config/DCLS/models/modules/dcls_arch.py unverified MIT (permissive) · 5d00cb9592e350f6 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Deep Constrained Least Squares (DCLS) (graph method: Deep Constrained Least Squares (DCLS)). 6 bricks; individually on a fixture: 0 ran · 6 unverified. The assembly has not been run end-to-end.

  1. DCLS entry · level 0 · unverified · 33653a69fe625918
  2. Estimator model · level 0 · unverified · 8fa6861f618410ad
  3. Restorer model · level 0 · unverified · 5d00cb9592e350f6
  4. CLS model · level 0 · unverified · 99aa6966a166e993
  5. DPCAG model · level 0 · unverified · 07a1c6d96c7e56c1
  6. DPCAB model · level 0 · unverified · 6d17723c7dd847a6

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2202.07508") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Blind Super-ResolutionDeblurringImage RestorationImage Super-ResolutionSuper-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Blind Super-Resolution BSD100 - 2x upscaling DCLS PSNR 32.04 #1 of 3 Archive leaderboard report
Blind Super-Resolution BSD100 - 2x upscaling DCLS SSIM 0.8907 #1 of 3 Archive leaderboard report
Blind Super-Resolution BSD100 - 3x upscaling DCLS PSNR 29.07 #1 of 2 Archive leaderboard report
Blind Super-Resolution BSD100 - 3x upscaling DCLS SSIM 0.7956 #1 of 2 Archive leaderboard report
Blind Super-Resolution BSD100 - 4x upscaling DCLS PSNR 27.6 #1 of 3 Archive leaderboard report
Blind Super-Resolution BSD100 - 4x upscaling DCLS SSIM 0.7285 #1 of 3 Archive leaderboard report
Blind Super-Resolution DIV2KRK - 2x upscaling DCLS PSNR 32.75 #1 of 5 Archive leaderboard report
Blind Super-Resolution DIV2KRK - 2x upscaling DCLS SSIM 0.9094 #1 of 5 Archive leaderboard report
Blind Super-Resolution DIV2KRK - 4x upscaling DCLS PSNR 28.99 #1 of 6 Archive leaderboard report
Blind Super-Resolution DIV2KRK - 4x upscaling DCLS SSIM 0.7946 #1 of 6 Archive leaderboard report
Blind Super-Resolution Manga109 - 2x upscaling DCLS PSNR 38.31 #1 of 3 Archive leaderboard report
Blind Super-Resolution Manga109 - 2x upscaling DCLS SSIM 0.974 #1 of 3 Archive leaderboard report
Blind Super-Resolution Manga109 - 3x upscaling DCLS PSNR 33.54 #1 of 2 Archive leaderboard report
Blind Super-Resolution Manga109 - 3x upscaling DCLS SSIM 0.9414 #1 of 2 Archive leaderboard report
Blind Super-Resolution Manga109 - 4x upscaling DCLS PSNR 30.86 #1 of 3 Archive leaderboard report
Blind Super-Resolution Manga109 - 4x upscaling DCLS SSIM 0.9086 #1 of 3 Archive leaderboard report
Blind Super-Resolution Set14 - 2x upscaling DCLS PSNR 33.46 #1 of 3 Archive leaderboard report
Blind Super-Resolution Set14 - 2x upscaling DCLS SSIM 0.9103 #1 of 3 Archive leaderboard report
Blind Super-Resolution Set14 - 3x upscaling DCLS PSNR 30.29 #1 of 2 Archive leaderboard report
Blind Super-Resolution Set14 - 3x upscaling DCLS SSIM 0.8329 #1 of 2 Archive leaderboard report
Blind Super-Resolution Set14 - 4x upscaling DCLS PSNR 28.54 #1 of 3 Archive leaderboard report
Blind Super-Resolution Set14 - 4x upscaling DCLS SSIM 0.7728 #1 of 3 Archive leaderboard report
Blind Super-Resolution Set5 - 2x upscaling DCLS PSNR 37.63 #1 of 3 Archive leaderboard report
Blind Super-Resolution Set5 - 2x upscaling DCLS SSIM 0.9554 #1 of 3 Archive leaderboard report
Blind Super-Resolution Set5 - 3x upscaling DCLS PSNR 34.21 #1 of 2 Archive leaderboard report
Blind Super-Resolution Set5 - 3x upscaling DCLS SSIM 0.9218 #1 of 2 Archive leaderboard report
Blind Super-Resolution Set5 - 4x upscaling DCLS PSNR 32.12 #1 of 3 Archive leaderboard report
Blind Super-Resolution Set5 - 4x upscaling DCLS SSIM 0.889 #1 of 3 Archive leaderboard report
Blind Super-Resolution Urban100 - 2x upscaling DCLS PSNR 31.69 #1 of 3 Archive leaderboard report
Blind Super-Resolution Urban100 - 2x upscaling DCLS SSIM 0.9202 #1 of 3 Archive leaderboard report
Blind Super-Resolution Urban100 - 3x upscaling DCLS PSNR 28.03 #1 of 2 Archive leaderboard report
Blind Super-Resolution Urban100 - 3x upscaling DCLS SSIM 0.8444 #1 of 2 Archive leaderboard report
Blind Super-Resolution Urban100 - 4x upscaling DCLS PSNR 26.15 #1 of 3 Archive leaderboard report
Blind Super-Resolution Urban100 - 4x upscaling DCLS SSIM 0.7809 #1 of 3 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