Underwater Image Super-Resolution using Generative Adversarial Network-based Model

TL;DR

This paper fine-tunes a state-of-the-art GAN-based super-resolution model for underwater images, significantly improving visual quality and realism, which benefits underwater exploration and autonomous vehicle vision tasks.

Contribution

It introduces a fine-tuning approach for Real-ESRGAN specifically for underwater images, enhancing its performance and realism compared to the original model.

Findings

Enhanced visual quality of underwater images

More realistic super-resolved images

Improved performance on USR-248 dataset

Abstract

Single image super-resolution (SISR) models are able to enhance the resolution and visual quality of underwater images and contribute to a better understanding of underwater environments. The integration of these models in Autonomous Underwater Vehicles (AUVs) can improve their performance in vision-based tasks. Real-Enhanced Super-Resolution Generative Adversarial Network (Real-ESRGAN) is an efficient model that has shown remarkable performance among SISR models. In this paper, we fine-tune the pre-trained Real-ESRGAN model for underwater image super-resolution. To fine-tune and evaluate the performance of the model, we use the USR-248 dataset. The fine-tuned model produces more realistic images with better visual quality compared to the Real-ESRGAN model.