HQ-50K: A Large-scale, High-quality Dataset for Image Restoration

TL;DR

This paper introduces HQ-50K, a comprehensive high-quality dataset for image restoration, and a versatile DAMoE model that effectively handles multiple corruption types and levels, advancing the state-of-the-art in the field.

Contribution

The paper presents a new large-scale, high-quality dataset HQ-50K and a novel Degradation-Aware Mixture of Expert (DAMoE) model for multi-task image restoration.

Findings

HQ-50K improves performance across various restoration tasks.

DAMoE outperforms existing models on multiple restoration levels.

The dataset covers diverse textures and semantic content.

Abstract

This paper introduces a new large-scale image restoration dataset, called HQ-50K, which contains 50,000 high-quality images with rich texture details and semantic diversity. We analyze existing image restoration datasets from five different perspectives, including data scale, resolution, compression rates, texture details, and semantic coverage. However, we find that all of these datasets are deficient in some aspects. In contrast, HQ-50K considers all of these five aspects during the data curation process and meets all requirements. We also present a new Degradation-Aware Mixture of Expert (DAMoE) model, which enables a single model to handle multiple corruption types and unknown levels. Our extensive experiments demonstrate that HQ-50K consistently improves the performance on various image restoration tasks, such as super-resolution, denoising, dejpeg, and deraining. Furthermore, our proposed DAMoE, trained on our \dataset, outperforms existing state-of-the-art unified models designed for multiple restoration tasks and levels. The dataset and code are available at \url{https://github.com/littleYaang/HQ-50K}.