Papers › Controlling Vision-Language Models for Multi-Task Image Restoration

Controlling Vision-Language Models for Multi-Task Image Restoration

2 Oct 2023arXiv:2310.01018archive 2025-07-28

Ziwei Luo, Fredrik K. Gustafsson, Zheng Zhao, Jens Sjölund, Thomas B. Schön

Vision-language models such as CLIP have shown great impact on diverse downstream tasks for zero-shot or label-free predictions. However, when it comes to low-level vision such as image restoration their performance deteriorates dramatically due to corrupted inputs. In this paper, we present a degradation-aware vision-language model (DA-CLIP) to better transfer pretrained vision-language models to low-level vision tasks as a multi-task framework for image restoration. More specifically, DA-CLIP trains an additional controller that adapts the fixed CLIP image encoder to predict high-quality feature embeddings. By integrating the embedding into an image restoration network via cross-attention, we are able to pilot the model to learn a high-fidelity image reconstruction. The controller itself will also output a degradation feature that matches the real corruptions of the input, yielding a natural classifier for different degradation types. In addition, we construct a mixed degradation dataset with synthetic captions for DA-CLIP training. Our approach advances state-of-the-art performance on both \emph{degradation-specific} and \emph{unified} image restoration tasks, showing a promising direction of prompting image restoration with large-scale pretrained vision-language models. Our code is available at https://github.com/Algolzw/daclip-uir.

PaperPDFCodeCode 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="2310.01018")

Code

Syntology Ran 8 of 9 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 2 ran · violated contract; 3 ran · our draft was wrong; 3 ran with no contract checked.

By repository: official repository: 9 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

algolzw/daclip-uir officialmentioned in papermentioned 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

9 samples harvested; 8 ran; 0 honoured the contract we drafted; 1 has 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 · violated contract
3ran · our draft was wrong
3ran
1unverified

Licence: 0 of the 9 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 Algolzw/daclip-uir. “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.

clip_transform Algolzw/daclip-uir/predict.py official repository ran MIT (permissive) · 5bd91c26df3f35f1 · report
default Algolzw/daclip-uir/universal-image-restoration/config/daclip-sde/models/modules/attention.py official repository ran · violated contract MIT (permissive) · 424012cb37b31172 · report
dict2str Algolzw/daclip-uir/universal-image-restoration/config/daclip-sde/options.py official repository ran · our draft was wrong MIT (permissive) · 40c52ad98161c17b · report
dict_to_nonedict Algolzw/daclip-uir/universal-image-restoration/config/daclip-sde/options.py official repository ran · our draft was wrong MIT (permissive) · ada7273eee7081c7 · report
exists Algolzw/daclip-uir/universal-image-restoration/config/daclip-sde/models/modules/attention.py official repository ran · violated contract MIT (permissive) · aa5486a3650902d8 · report
get_paths_from_images Algolzw/daclip-uir/da-clip/src/evaluate.py official repository ran MIT (permissive) · f51268128919f88a · report
is_image_file Algolzw/daclip-uir/da-clip/src/evaluate.py official repository ran MIT (permissive) · 49c770cc5e58f787 · report
uniq Algolzw/daclip-uir/universal-image-restoration/config/daclip-sde/models/modules/attention.py official repository ran · our draft was wrong MIT (permissive) · 9a299fe5ae09e407 · report
parse Algolzw/daclip-uir/universal-image-restoration/config/daclip-sde/options.py official repository unverified MIT (permissive) · 9a64f79c73dd7f45 · report

Tasks

Image DehazingImage DenoisingImage InpaintingImage ReconstructionImage RestorationJPEG Artifact RemovalLanguage ModellingLow-Light Image EnhancementRain RemovalShadow RemovalSingle Image DerainingUnified Image Restoration

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Dehazing RESIDE-6K DA-CLIP PSNR 30.16 #3 of 6 Archive leaderboard report
Image Dehazing RESIDE-6K DA-CLIP SSIM 0.936 #3 of 6 Archive leaderboard report
Low-Light Image Enhancement LOL DA-CLIP Average PSNR 23.77 #27 of 40 Archive leaderboard report
Low-Light Image Enhancement LOL DA-CLIP LPIPS 0.083 #27 of 40 Archive leaderboard report
Low-Light Image Enhancement LOL DA-CLIP SSIM 0.830 #27 of 40 Archive leaderboard report
Single Image Deraining Rain100H DA-CLIP PSNR 33.91 #2 of 19 Archive leaderboard report
Single Image Deraining Rain100H DA-CLIP SSIM 0.926 #2 of 19 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

CLIPDiffusion

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