{"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/improving-image-restoration-through-removing","title":"Improving Image Restoration through Removing Degradations in Textual Representations","arxiv_id":"2312.17334","date":"2023-12-28","proceeding":"CVPR 2024 1","authors":["Jingbo Lin","Zhilu Zhang","Yuxiang Wei","Dongwei Ren","Dongsheng Jiang","WangMeng Zuo"],"abstract":"In this paper, we introduce a new perspective for improving image restoration by removing degradation in the textual representations of a given degraded image. Intuitively, restoration is much easier on text modality than image one. For example, it can be easily conducted by removing degradation-related words while keeping the content-aware words. Hence, we combine the advantages of images in detail description and ones of text in degradation removal to perform restoration. To address the cross-modal assistance, we propose to map the degraded images into textual representations for removing the degradations, and then convert the restored textual representations into a guidance image for assisting image restoration. In particular, We ingeniously embed an image-to-text mapper and text restoration module into CLIP-equipped text-to-image models to generate the guidance. Then, we adopt a simple coarse-to-fine approach to dynamically inject multi-scale information from guidance to image restoration networks. Extensive experiments are conducted on various image restoration tasks, including deblurring, dehazing, deraining, and denoising, and all-in-one image restoration. The results showcase that our method outperforms state-of-the-art ones across all these tasks. The codes and models are available at \\url{https://github.com/mrluin/TextualDegRemoval}.","url_abs":"https://arxiv.org/abs/2312.17334v1","url_pdf":"https://arxiv.org/pdf/2312.17334v1.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":"improving-image-restoration-through-removing","repo_url":"https://github.com/mrluin/textualdegremoval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"deblurring","task_name":"Deblurring"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"image-to-text","task_name":"Image to text"},{"task_slug":"rain-removal","task_name":"Rain Removal"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.17334","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}