Perceive-IR: Learning to Perceive Degradation Better for All-in-One Image Restoration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Xu, Ma, Jiaqi, Wang, Guoli, Zhang, Qian, Zhang, Huan, Zhang, Lefei
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915276669321216
author Zhang, Xu
Ma, Jiaqi
Wang, Guoli
Zhang, Qian
Zhang, Huan
Zhang, Lefei
author_facet Zhang, Xu
Ma, Jiaqi
Wang, Guoli
Zhang, Qian
Zhang, Huan
Zhang, Lefei
contents Existing All-in-One image restoration methods often fail to perceive degradation types and severity levels simultaneously, overlooking the importance of fine-grained quality perception. Moreover, these methods often utilize highly customized backbones, which hinder their adaptability and integration into more advanced restoration networks. To address these limitations, we propose Perceive-IR, a novel backbone-agnostic All-in-One image restoration framework designed for fine-grained quality control across various degradation types and severity levels. Its modular structure allows core components to function independently of specific backbones, enabling seamless integration into advanced restoration models without significant modifications. Specifically, Perceive-IR operates in two key stages: 1) multi-level quality-driven prompt learning stage, where a fine-grained quality perceiver is meticulously trained to discern three tier quality levels by optimizing the alignment between prompts and images within the CLIP perception space. This stage ensures a nuanced understanding of image quality, laying the groundwork for subsequent restoration; 2) restoration stage, where the quality perceiver is seamlessly integrated with a difficulty-adaptive perceptual loss, forming a quality-aware learning strategy. This strategy not only dynamically differentiates sample learning difficulty but also achieves fine-grained quality control by driving the restored image toward the ground truth while pulling it away from both low- and medium-quality samples.
format Preprint
id arxiv_https___arxiv_org_abs_2408_15994
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Perceive-IR: Learning to Perceive Degradation Better for All-in-One Image Restoration
Zhang, Xu
Ma, Jiaqi
Wang, Guoli
Zhang, Qian
Zhang, Huan
Zhang, Lefei
Computer Vision and Pattern Recognition
Existing All-in-One image restoration methods often fail to perceive degradation types and severity levels simultaneously, overlooking the importance of fine-grained quality perception. Moreover, these methods often utilize highly customized backbones, which hinder their adaptability and integration into more advanced restoration networks. To address these limitations, we propose Perceive-IR, a novel backbone-agnostic All-in-One image restoration framework designed for fine-grained quality control across various degradation types and severity levels. Its modular structure allows core components to function independently of specific backbones, enabling seamless integration into advanced restoration models without significant modifications. Specifically, Perceive-IR operates in two key stages: 1) multi-level quality-driven prompt learning stage, where a fine-grained quality perceiver is meticulously trained to discern three tier quality levels by optimizing the alignment between prompts and images within the CLIP perception space. This stage ensures a nuanced understanding of image quality, laying the groundwork for subsequent restoration; 2) restoration stage, where the quality perceiver is seamlessly integrated with a difficulty-adaptive perceptual loss, forming a quality-aware learning strategy. This strategy not only dynamically differentiates sample learning difficulty but also achieves fine-grained quality control by driving the restored image toward the ground truth while pulling it away from both low- and medium-quality samples.
title Perceive-IR: Learning to Perceive Degradation Better for All-in-One Image Restoration
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.15994