ClearAIR: A Human-Visual-Perception-Inspired All-in-One Image Restoration

TL;DR

ClearAIR introduces a hierarchical, human-visual-perception-inspired framework for all-in-one image restoration, utilizing multimodal assessment, semantic guidance, and self-supervised detail enhancement to outperform existing methods.

Contribution

The paper presents a novel AiOIR framework inspired by human visual perception, integrating multimodal IQA, semantic cross-attention, and self-supervised internal clue reuse for improved image restoration.

Findings

Achieves superior performance on synthetic and real-world datasets.

Effectively captures complex degradations with region-aware modules.

Enhances detail restoration through self-supervised internal clue reuse.

Abstract

All-in-One Image Restoration (AiOIR) has advanced significantly, offering promising solutions for complex real-world degradations. However, most existing approaches rely heavily on degradation-specific representations, often resulting in oversmoothing and artifacts. To address this, we propose ClearAIR, a novel AiOIR framework inspired by Human Visual Perception (HVP) and designed with a hierarchical, coarse-to-fine restoration strategy. First, leveraging the global priority of early HVP, we employ a Multimodal Large Language Model (MLLM)-based Image Quality Assessment (IQA) model for overall evaluation. Unlike conventional IQA, our method integrates cross-modal understanding to more accurately characterize complex, composite degradations. Building upon this overall assessment, we then introduce a region awareness and task recognition pipeline. A semantic cross-attention, leveraging semantic guidance unit, first produces coarse semantic prompts. Guided by this regional context, a degradation-aware module implicitly captures region-specific degradation characteristics, enabling more precise local restoration. Finally, to recover fine details, we propose an internal clue reuse mechanism. It operates in a self-supervised manner to mine and leverage the intrinsic information of the image itself, substantially enhancing detail restoration. Experimental results show that ClearAIR achieves superior performance across diverse synthetic and real-world datasets.