{"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/autodir-automatic-all-in-one-image","title":"AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusion","arxiv_id":"2310.10123","date":"2023-10-16","proceeding":null,"authors":["Yitong Jiang","Zhaoyang Zhang","Tianfan Xue","Jinwei Gu"],"abstract":"We present AutoDIR, an innovative all-in-one image restoration system incorporating latent diffusion. AutoDIR excels in its ability to automatically identify and restore images suffering from a range of unknown degradations. AutoDIR offers intuitive open-vocabulary image editing, empowering users to customize and enhance images according to their preferences. Specifically, AutoDIR consists of two key stages: a Blind Image Quality Assessment (BIQA) stage based on a semantic-agnostic vision-language model which automatically detects unknown image degradations for input images, an All-in-One Image Restoration (AIR) stage utilizes structural-corrected latent diffusion which handles multiple types of image degradations. Extensive experimental evaluation demonstrates that AutoDIR outperforms state-of-the-art approaches for a wider range of image restoration tasks. The design of AutoDIR also enables flexible user control (via text prompt) and generalization to new tasks as a foundation model of image restoration. Project is available at: \\url{https://jiangyitong.github.io/AutoDIR_webpage/}.","url_abs":"https://arxiv.org/abs/2310.10123v5","url_pdf":"https://arxiv.org/pdf/2310.10123v5.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":"autodir-automatic-all-in-one-image","repo_url":"https://github.com/jiangyitong/AutoDIR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"image-quality-assessment","task_name":"Image Quality Assessment"},{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"no-reference-image-quality-assessment","task_name":"No-Reference Image Quality Assessment"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.10123","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}