Papers › MoE-DiffIR: Task-customized Diffusion Priors for Universal Compressed Image Restoration

MoE-DiffIR: Task-customized Diffusion Priors for Universal Compressed Image Restoration

15 Jul 2024arXiv:2407.10833archive 2025-07-28

Yulin Ren, Xin Li, Bingchen Li, Xingrui Wang, Mengxi Guo, Shijie Zhao, Li Zhang, Zhibo Chen

We present MoE-DiffIR, an innovative universal compressed image restoration (CIR) method with task-customized diffusion priors. This intends to handle two pivotal challenges in the existing CIR methods: (i) lacking adaptability and universality for different image codecs, e.g., JPEG and WebP; (ii) poor texture generation capability, particularly at low bitrates. Specifically, our MoE-DiffIR develops the powerful mixture-of-experts (MoE) prompt module, where some basic prompts cooperate to excavate the task-customized diffusion priors from Stable Diffusion (SD) for each compression task. Moreover, the degradation-aware routing mechanism is proposed to enable the flexible assignment of basic prompts. To activate and reuse the cross-modality generation prior of SD, we design the visual-to-text adapter for MoE-DiffIR, which aims to adapt the embedding of low-quality images from the visual domain to the textual domain as the textual guidance for SD, enabling more consistent and reasonable texture generation. We also construct one comprehensive benchmark dataset for universal CIR, covering 21 types of degradations from 7 popular traditional and learned codecs. Extensive experiments on universal CIR have demonstrated the excellent robustness and texture restoration capability of our proposed MoE-DiffIR. The project can be found at https://renyulin-f.github.io/MoE-DiffIR.github.io/.

PaperPDFCode 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="2407.10833")

Code

Syntology Ran 8 of 11 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 8 ran with no contract checked.

By repository: found in paper text by Syntology: 11 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.

Justin-Tan/high-fidelity-generative-compression found in paper text by SyntologyApache-2.0 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

11 samples harvested; 8 ran; 0 honoured the contract we drafted; 3 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.

8ran
3unverified

Licence: 0 of the 11 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 Justin-Tan/high-fidelity-generative-compression. “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.

empty_message Justin-Tan/high-fidelity-generative-compression/src/compression/ans.py found in paper text by Syntology ran Apache-2.0 (permissive) · cdd42fd1996f0d00 · report
pmf_to_quantized_cdf Justin-Tan/high-fidelity-generative-compression/src/helpers/maths.py found in paper text by Syntology ran Apache-2.0 (permissive) · 8169fb353c1eddce · report
prior_scale_table Justin-Tan/high-fidelity-generative-compression/src/compression/prior_model.py found in paper text by Syntology ran Apache-2.0 (permissive) · db553ee9f96641cd · report
stack_extend Justin-Tan/high-fidelity-generative-compression/src/compression/ans.py found in paper text by Syntology ran Apache-2.0 (permissive) · be6081790a78bd00 · report
stack_slice Justin-Tan/high-fidelity-generative-compression/src/compression/ans.py found in paper text by Syntology ran Apache-2.0 (permissive) · c2290958ec105f86 · report
standardized_CDF_gaussian Justin-Tan/high-fidelity-generative-compression/src/helpers/maths.py found in paper text by Syntology ran fingerprinted Apache-2.0 (permissive) · 3bc31588e9eaef4f · report
standardized_CDF_logistic Justin-Tan/high-fidelity-generative-compression/src/helpers/maths.py found in paper text by Syntology ran fingerprinted Apache-2.0 (permissive) · aa2e81dea4597c5e · report
view_update Justin-Tan/high-fidelity-generative-compression/src/compression/compression_utils.py found in paper text by Syntology ran Apache-2.0 (permissive) · 0b12296531c3532e · report
get_background Justin-Tan/high-fidelity-generative-compression/src/helpers/datasets.py found in paper text by Syntology unverified Apache-2.0 (permissive) · 839001b755552a0b · report
get_dataset Justin-Tan/high-fidelity-generative-compression/src/helpers/datasets.py found in paper text by Syntology unverified Apache-2.0 (permissive) · 4bde06f8d5798cfa · report
get_img_size Justin-Tan/high-fidelity-generative-compression/src/helpers/datasets.py found in paper text by Syntology unverified Apache-2.0 (permissive) · bc54c1e183c90aa3 · report

Tasks

Image RestorationMixture-of-ExpertsTexture Synthesis

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdapterDiffusion

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