Multi-modal Datasets for Super-resolution
This addresses the need for more diverse training data in super-resolution for real-world applications, though it is incremental as it focuses on dataset creation rather than novel algorithms.
The authors tackled the problem of limited robustness and generalization in super-resolution models by introducing two new datasets: OID-RW for real-world black-and-white old photos and MDD400 for multi-modal degradation scenarios, resulting in models with better generalization, robustness, and improved edge contours and texture features.
Nowdays, most datasets used to train and evaluate super-resolution models are single-modal simulation datasets. However, due to the variety of image degradation types in the real world, models trained on single-modal simulation datasets do not always have good robustness and generalization ability in different degradation scenarios. Previous work tended to focus only on true-color images. In contrast, we first proposed real-world black-and-white old photo datasets for super-resolution (OID-RW), which is constructed using two methods of manually filling pixels and shooting with different cameras. The dataset contains 82 groups of images, including 22 groups of character type and 60 groups of landscape and architecture. At the same time, we also propose a multi-modal degradation dataset (MDD400) to solve the super-resolution reconstruction in real-life image degradation scenarios. We managed to simulate the process of generating degraded images by the following four methods: interpolation algorithm, CNN network, GAN network and capturing videos with different bit rates. Our experiments demonstrate that not only the models trained on our dataset have better generalization capability and robustness, but also the trained images can maintain better edge contours and texture features.