{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/moe-diffir-task-customized-diffusion-priors","title":"MoE-DiffIR: Task-customized Diffusion Priors for Universal Compressed Image Restoration","arxiv_id":"2407.10833","date":"2024-07-15","proceeding":null,"authors":["Yulin Ren","Xin Li","Bingchen Li","Xingrui Wang","Mengxi Guo","Shijie Zhao","Li Zhang","Zhibo Chen"],"abstract":"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/.","url_abs":"https://arxiv.org/abs/2407.10833v1","url_pdf":"https://arxiv.org/pdf/2407.10833v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"},{"task_slug":"texture-synthesis","task_name":"Texture Synthesis"}],"methods":[{"method_slug":"adapter","method_name":"Adapter"},{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.10833","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.10833"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/Justin-Tan/high-fidelity-generative-compression","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":8,"unverified":3},"by_repo_kind":{"found_in_text":{"samples":11,"ran":8,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"cdd42fd1996f0d00","entry":"empty_message","repo":"Justin-Tan/high-fidelity-generative-compression","repo_kind":"found_in_text","path":"src/compression/ans.py","file_url":"https://github.com/Justin-Tan/high-fidelity-generative-compression/blob/HEAD/src/compression/ans.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cdd42fd1996f0d00"}},{"code_sha256_prefix":"8169fb353c1eddce","entry":"pmf_to_quantized_cdf","repo":"Justin-Tan/high-fidelity-generative-compression","repo_kind":"found_in_text","path":"src/helpers/maths.py","file_url":"https://github.com/Justin-Tan/high-fidelity-generative-compression/blob/HEAD/src/helpers/maths.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8169fb353c1eddce"}},{"code_sha256_prefix":"db553ee9f96641cd","entry":"prior_scale_table","repo":"Justin-Tan/high-fidelity-generative-compression","repo_kind":"found_in_text","path":"src/compression/prior_model.py","file_url":"https://github.com/Justin-Tan/high-fidelity-generative-compression/blob/HEAD/src/compression/prior_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"db553ee9f96641cd"}},{"code_sha256_prefix":"be6081790a78bd00","entry":"stack_extend","repo":"Justin-Tan/high-fidelity-generative-compression","repo_kind":"found_in_text","path":"src/compression/ans.py","file_url":"https://github.com/Justin-Tan/high-fidelity-generative-compression/blob/HEAD/src/compression/ans.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"be6081790a78bd00"}},{"code_sha256_prefix":"c2290958ec105f86","entry":"stack_slice","repo":"Justin-Tan/high-fidelity-generative-compression","repo_kind":"found_in_text","path":"src/compression/ans.py","file_url":"https://github.com/Justin-Tan/high-fidelity-generative-compression/blob/HEAD/src/compression/ans.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c2290958ec105f86"}},{"code_sha256_prefix":"3bc31588e9eaef4f","entry":"standardized_CDF_gaussian","repo":"Justin-Tan/high-fidelity-generative-compression","repo_kind":"found_in_text","path":"src/helpers/maths.py","file_url":"https://github.com/Justin-Tan/high-fidelity-generative-compression/blob/HEAD/src/helpers/maths.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3bc31588e9eaef4f"}},{"code_sha256_prefix":"aa2e81dea4597c5e","entry":"standardized_CDF_logistic","repo":"Justin-Tan/high-fidelity-generative-compression","repo_kind":"found_in_text","path":"src/helpers/maths.py","file_url":"https://github.com/Justin-Tan/high-fidelity-generative-compression/blob/HEAD/src/helpers/maths.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aa2e81dea4597c5e"}},{"code_sha256_prefix":"0b12296531c3532e","entry":"view_update","repo":"Justin-Tan/high-fidelity-generative-compression","repo_kind":"found_in_text","path":"src/compression/compression_utils.py","file_url":"https://github.com/Justin-Tan/high-fidelity-generative-compression/blob/HEAD/src/compression/compression_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0b12296531c3532e"}},{"code_sha256_prefix":"839001b755552a0b","entry":"get_background","repo":"Justin-Tan/high-fidelity-generative-compression","repo_kind":"found_in_text","path":"src/helpers/datasets.py","file_url":"https://github.com/Justin-Tan/high-fidelity-generative-compression/blob/HEAD/src/helpers/datasets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"839001b755552a0b"}},{"code_sha256_prefix":"4bde06f8d5798cfa","entry":"get_dataset","repo":"Justin-Tan/high-fidelity-generative-compression","repo_kind":"found_in_text","path":"src/helpers/datasets.py","file_url":"https://github.com/Justin-Tan/high-fidelity-generative-compression/blob/HEAD/src/helpers/datasets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4bde06f8d5798cfa"}},{"code_sha256_prefix":"bc54c1e183c90aa3","entry":"get_img_size","repo":"Justin-Tan/high-fidelity-generative-compression","repo_kind":"found_in_text","path":"src/helpers/datasets.py","file_url":"https://github.com/Justin-Tan/high-fidelity-generative-compression/blob/HEAD/src/helpers/datasets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bc54c1e183c90aa3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}