Improving Image Restoration through Removing Degradations in Textual Representations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lin, Jingbo, Zhang, Zhilu, Wei, Yuxiang, Ren, Dongwei, Jiang, Dongsheng, Zuo, Wangmeng
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909056830013440
author Lin, Jingbo
Zhang, Zhilu
Wei, Yuxiang
Ren, Dongwei
Jiang, Dongsheng
Zuo, Wangmeng
author_facet Lin, Jingbo
Zhang, Zhilu
Wei, Yuxiang
Ren, Dongwei
Jiang, Dongsheng
Zuo, Wangmeng
contents 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}.
format Preprint
id arxiv_https___arxiv_org_abs_2312_17334
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Improving Image Restoration through Removing Degradations in Textual Representations
Lin, Jingbo
Zhang, Zhilu
Wei, Yuxiang
Ren, Dongwei
Jiang, Dongsheng
Zuo, Wangmeng
Computer Vision and Pattern Recognition
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}.
title Improving Image Restoration through Removing Degradations in Textual Representations
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.17334