HQ-50K: A Large-scale, High-quality Dataset for Image Restoration
This addresses the problem of limited and deficient datasets for researchers and practitioners in image restoration, offering a high-quality resource and a novel model, though it is incremental in dataset creation.
The paper tackles the lack of comprehensive datasets for image restoration by introducing HQ-50K, a large-scale dataset of 50,000 high-quality images that improves performance across tasks like super-resolution and denoising, and proposes a Degradation-Aware Mixture of Expert model that outperforms existing unified models.
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}.