# Underwater Image Super-Resolution using Deep Residual Multipliers

arXiv: https://arxiv.org/abs/1909.09437 · HTML: https://mlsanity.com/paper/1909.09437/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Sep 2019.

## Built on by (most cited first, 7 of 7)

- [Wavelength-based Attributed Deep Neural Network for Underwater Image Restoration](https://mlsanity.com/paper/2106.07910/) (2021)
- [Robotic Detection of a Human-Comprehensible Gestural Language for Underwater Multi-Human-Robot Collaboration](https://mlsanity.com/paper/2207.05331/) (2022)
- [A deep learning approach for marine snow synthesis and removal](https://mlsanity.com/paper/2311.15584/) (2023)
- [Virtual Underwater Datasets for Autonomous Inspections](https://mlsanity.com/paper/2209.06013/) (2022)
- [UStyle: Waterbody Style Transfer of Underwater Scenes by Depth-Guided Feature Synthesis](https://mlsanity.com/paper/2503.11893/) (2025)
- [A Diver Attention Estimation Framework for Effective Underwater Human-Robot Interaction](https://mlsanity.com/paper/2209.14447/) (2022)
- [Underwater Image Super-Resolution using Generative Adversarial Network-based Model](https://mlsanity.com/paper/2211.03550/) (2022)

## Abstract (arXiv)

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 textitperceptual 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.