OneRestore: A Universal Restoration Framework for Composite Degradation

TL;DR

OneRestore is a transformer-based framework that effectively restores images affected by multiple simultaneous degradations like haze, rain, snow, and low light, outperforming existing methods on synthetic and real-world data.

Contribution

The paper introduces a versatile imaging model for complex degradations and a novel transformer-based restoration framework with a unique cross-attention mechanism and composite degradation loss.

Findings

Outperforms existing methods on synthetic datasets

Effectively handles real-world composite degradations

Demonstrates versatility with various input scene descriptors

Abstract

In real-world scenarios, image impairments often manifest as composite degradations, presenting a complex interplay of elements such as low light, haze, rain, and snow. Despite this reality, existing restoration methods typically target isolated degradation types, thereby falling short in environments where multiple degrading factors coexist. To bridge this gap, our study proposes a versatile imaging model that consolidates four physical corruption paradigms to accurately represent complex, composite degradation scenarios. In this context, we propose OneRestore, a novel transformer-based framework designed for adaptive, controllable scene restoration. The proposed framework leverages a unique cross-attention mechanism, merging degraded scene descriptors with image features, allowing for nuanced restoration. Our model allows versatile input scene descriptors, ranging from manual text embeddings to automatic extractions based on visual attributes. Our methodology is further enhanced through a composite degradation restoration loss, using extra degraded images as negative samples to fortify model constraints. Comparative results on synthetic and real-world datasets demonstrate OneRestore as a superior solution, significantly advancing the state-of-the-art in addressing complex, composite degradations.