Underwater Image Super-Resolution using Deep Residual Multipliers

TL;DR

This paper introduces a deep residual generative model for underwater image super-resolution, utilizing adversarial training and a new dataset, to improve image quality for autonomous underwater robots.

Contribution

It presents a novel deep residual network architecture with an adversarial training pipeline and introduces USR-248, a large-scale dataset for supervised underwater image super-resolution.

Findings

The model outperforms several state-of-the-art super-resolution methods.

Qualitative and quantitative results validate the effectiveness of the approach.

The method is feasible for practical underwater scene understanding applications.

Abstract

We present a deep residual network-based generative model for single image super-resolution (SISR) of underwater imagery for use by autonomous underwater robots. We also provide an adversarial training pipeline for learning SISR from paired data. In order to supervise the training, we formulate an objective function that evaluates the \textit{perceptual quality} of an image based on its global content, color, and local style information. Additionally, we present USR-248, a large-scale dataset of three sets of underwater images of 'high' (640x480) and 'low' (80x60, 160x120, and 320x240) spatial resolution. USR-248 contains paired instances for supervised training of 2x, 4x, or 8x SISR models. Furthermore, we validate the effectiveness of our proposed model through qualitative and quantitative experiments and compare the results with several state-of-the-art models' performances. We also analyze its practical feasibility for applications such as scene understanding and attention modeling in noisy visual conditions.