{"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/refir-grounding-large-restoration-models-with","title":"ReFIR: Grounding Large Restoration Models with Retrieval Augmentation","arxiv_id":"2410.05601","date":"2024-10-08","proceeding":null,"authors":["Hang Guo","Tao Dai","Zhihao Ouyang","Taolin Zhang","Yaohua Zha","Bin Chen","Shu-Tao Xia"],"abstract":"Recent advances in diffusion-based Large Restoration Models (LRMs) have significantly improved photo-realistic image restoration by leveraging the internal knowledge embedded within model weights. However, existing LRMs often suffer from the hallucination dilemma, i.e., producing incorrect contents or textures when dealing with severe degradations, due to their heavy reliance on limited internal knowledge. In this paper, we propose an orthogonal solution called the Retrieval-augmented Framework for Image Restoration (ReFIR), which incorporates retrieved images as external knowledge to extend the knowledge boundary of existing LRMs in generating details faithful to the original scene. Specifically, we first introduce the nearest neighbor lookup to retrieve content-relevant high-quality images as reference, after which we propose the cross-image injection to modify existing LRMs to utilize high-quality textures from retrieved images. Thanks to the additional external knowledge, our ReFIR can well handle the hallucination challenge and facilitate faithfully results. Extensive experiments demonstrate that ReFIR can achieve not only high-fidelity but also realistic restoration results. Importantly, our ReFIR requires no training and is adaptable to various LRMs.","url_abs":"https://arxiv.org/abs/2410.05601v1","url_pdf":"https://arxiv.org/pdf/2410.05601v1.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":[{"paper_slug":"refir-grounding-large-restoration-models-with","repo_url":"https://github.com/csguoh/refir","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.05601","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05601"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/csguoh/refir","reach":null}],"summary":{"ran":1,"ran_draft_wrong":1,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":4,"samples":[{"code_sha256_prefix":"c1391ab9b1bfca0a","entry":"MutualSelfAttentionControl","repo":"csguoh/refir","repo_kind":"official","path":"seesr/seesr_register.py","file_url":"https://github.com/csguoh/refir/blob/HEAD/seesr/seesr_register.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c1391ab9b1bfca0a"}},{"code_sha256_prefix":"8884101c7509e8aa","entry":"adain_latentBHLC","repo":"csguoh/refir","repo_kind":"official","path":"seesr/seesr_register.py","file_url":"https://github.com/csguoh/refir/blob/HEAD/seesr/seesr_register.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8884101c7509e8aa"}},{"code_sha256_prefix":"775f3bb32c99d24d","entry":"cosine_schedule","repo":"csguoh/refir","repo_kind":"official","path":"seesr/seesr_register.py","file_url":"https://github.com/csguoh/refir/blob/HEAD/seesr/seesr_register.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"775f3bb32c99d24d"}},{"code_sha256_prefix":"cb6a491739f848e6","entry":"AttentionBase","repo":"csguoh/refir","repo_kind":"official","path":"seesr/seesr_register.py","file_url":"https://github.com/csguoh/refir/blob/HEAD/seesr/seesr_register.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cb6a491739f848e6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}