{"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/controlling-vision-language-models-for","title":"Controlling Vision-Language Models for Multi-Task Image Restoration","arxiv_id":"2310.01018","date":"2023-10-02","proceeding":null,"authors":["Ziwei Luo","Fredrik K. Gustafsson","Zheng Zhao","Jens Sjölund","Thomas B. Schön"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2310.01018v2","url_pdf":"https://arxiv.org/pdf/2310.01018v2.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":"controlling-vision-language-models-for","repo_url":"https://github.com/algolzw/daclip-uir","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-dehazing","task_name":"Image Dehazing"},{"task_slug":"image-denoising","task_name":"Image Denoising"},{"task_slug":"image-inpainting","task_name":"Image Inpainting"},{"task_slug":"image-reconstruction","task_name":"Image Reconstruction"},{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"jpeg-artifact-removal","task_name":"JPEG Artifact Removal"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"low-light-image-enhancement","task_name":"Low-Light Image Enhancement"},{"task_slug":"rain-removal","task_name":"Rain Removal"},{"task_slug":"shadow-removal","task_name":"Shadow Removal"},{"task_slug":"single-image-deraining","task_name":"Single Image Deraining"},{"task_slug":"unified-image-restoration","task_name":"Unified Image Restoration"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-dehazing-on-reside-6k","task":"Image Dehazing","dataset":"RESIDE-6K","model":"DA-CLIP","rank_in_archive_order":3,"of":6,"metrics":{"PSNR":"30.16","SSIM":"0.936"},"uses_additional_data":false},{"leaderboard":"/sota/low-light-image-enhancement-on-lol","task":"Low-Light Image Enhancement","dataset":"LOL","model":"DA-CLIP","rank_in_archive_order":27,"of":40,"metrics":{"Average PSNR":"23.77","LPIPS":"0.083","SSIM":"0.830"},"uses_additional_data":false},{"leaderboard":"/sota/single-image-deraining-on-rain100h","task":"Single Image Deraining","dataset":"Rain100H","model":"DA-CLIP","rank_in_archive_order":2,"of":19,"metrics":{"PSNR":"33.91","SSIM":"0.926"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.01018","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01018"}},"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/Algolzw/daclip-uir","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/algolzw/daclip-uir","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"ran_violates":2,"ran_draft_wrong":3,"unverified":1},"by_repo_kind":{"official":{"samples":9,"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":"5bd91c26df3f35f1","entry":"clip_transform","repo":"Algolzw/daclip-uir","repo_kind":"official","path":"predict.py","file_url":"https://github.com/Algolzw/daclip-uir/blob/HEAD/predict.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5bd91c26df3f35f1"}},{"code_sha256_prefix":"424012cb37b31172","entry":"default","repo":"Algolzw/daclip-uir","repo_kind":"official","path":"universal-image-restoration/config/daclip-sde/models/modules/attention.py","file_url":"https://github.com/Algolzw/daclip-uir/blob/HEAD/universal-image-restoration/config/daclip-sde/models/modules/attention.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"424012cb37b31172"}},{"code_sha256_prefix":"40c52ad98161c17b","entry":"dict2str","repo":"Algolzw/daclip-uir","repo_kind":"official","path":"universal-image-restoration/config/daclip-sde/options.py","file_url":"https://github.com/Algolzw/daclip-uir/blob/HEAD/universal-image-restoration/config/daclip-sde/options.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"40c52ad98161c17b"}},{"code_sha256_prefix":"ada7273eee7081c7","entry":"dict_to_nonedict","repo":"Algolzw/daclip-uir","repo_kind":"official","path":"universal-image-restoration/config/daclip-sde/options.py","file_url":"https://github.com/Algolzw/daclip-uir/blob/HEAD/universal-image-restoration/config/daclip-sde/options.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ada7273eee7081c7"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"Algolzw/daclip-uir","repo_kind":"official","path":"universal-image-restoration/config/daclip-sde/models/modules/attention.py","file_url":"https://github.com/Algolzw/daclip-uir/blob/HEAD/universal-image-restoration/config/daclip-sde/models/modules/attention.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"f51268128919f88a","entry":"get_paths_from_images","repo":"Algolzw/daclip-uir","repo_kind":"official","path":"da-clip/src/evaluate.py","file_url":"https://github.com/Algolzw/daclip-uir/blob/HEAD/da-clip/src/evaluate.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f51268128919f88a"}},{"code_sha256_prefix":"49c770cc5e58f787","entry":"is_image_file","repo":"Algolzw/daclip-uir","repo_kind":"official","path":"da-clip/src/evaluate.py","file_url":"https://github.com/Algolzw/daclip-uir/blob/HEAD/da-clip/src/evaluate.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"49c770cc5e58f787"}},{"code_sha256_prefix":"9a299fe5ae09e407","entry":"uniq","repo":"Algolzw/daclip-uir","repo_kind":"official","path":"universal-image-restoration/config/daclip-sde/models/modules/attention.py","file_url":"https://github.com/Algolzw/daclip-uir/blob/HEAD/universal-image-restoration/config/daclip-sde/models/modules/attention.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9a299fe5ae09e407"}},{"code_sha256_prefix":"9a64f79c73dd7f45","entry":"parse","repo":"Algolzw/daclip-uir","repo_kind":"official","path":"universal-image-restoration/config/daclip-sde/options.py","file_url":"https://github.com/Algolzw/daclip-uir/blob/HEAD/universal-image-restoration/config/daclip-sde/options.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9a64f79c73dd7f45"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}