Detail Loss in Super-Resolution Models Based on the Laplacian Pyramid and Repeated Upscaling and Downscaling Process

TL;DR

This paper introduces a novel detail loss based on Laplacian pyramids and a repeated upscaling/downscaling process to improve high-frequency detail preservation in super-resolution images, achieving state-of-the-art results.

Contribution

It proposes a new detail loss and a repeated upscaling/downscaling method that enhance high-frequency details in super-resolution models, outperforming existing approaches.

Findings

State-of-the-art super-resolution results with CNN-based models.

Improved detail preservation in attention-based models using the proposed loss.

Enhanced high-frequency components across various model structures.

Abstract

With advances in artificial intelligence, image processing has gained significant interest. Image super-resolution is a vital technology closely related to real-world applications, as it enhances the quality of existing images. Since enhancing fine details is crucial for the super-resolution task, pixels that contribute to high-frequency information should be emphasized. This paper proposes two methods to enhance high-frequency details in super-resolution images: a Laplacian pyramid-based detail loss and a repeated upscaling and downscaling process. Total loss with our detail loss guides a model by separately generating and controlling super-resolution and detail images. This approach allows the model to focus more effectively on high-frequency components, resulting in improved super-resolution images. Additionally, repeated upscaling and downscaling amplify the effectiveness of the detail loss by extracting diverse information from multiple low-resolution features. We conduct two types of experiments. First, we design a CNN-based model incorporating our methods. This model achieves state-of-the-art results, surpassing all currently available CNN-based and even some attention-based models. Second, we apply our methods to existing attention-based models on a small scale. In all our experiments, attention-based models adding our detail loss show improvements compared to the originals. These results demonstrate our approaches effectively enhance super-resolution images across different model structures.