All-In-One Underwater Image Enhancement using Domain-Adversarial Learning

TL;DR

This paper introduces a domain-adversarial learning model for underwater image enhancement that effectively handles water type diversity, improving image quality and downstream vision tasks across various water conditions.

Contribution

A novel adversarial model that disentangles water type nuisances to produce domain-agnostic enhanced underwater images, outperforming previous methods.

Findings

Outperforms previous methods in SSIM and PSNR across water types

Generalizes well to real-world underwater images

Improves object detection performance using enhanced images

Abstract

Raw underwater images are degraded due to wavelength dependent light attenuation and scattering, limiting their applicability in vision systems. Another factor that makes enhancing underwater images particularly challenging is the diversity of the water types in which they are captured. For example, images captured in deep oceanic waters have a different distribution from those captured in shallow coastal waters. Such diversity makes it hard to train a single model to enhance underwater images. In this work, we propose a novel model which nicely handles the diversity of water during the enhancement, by adversarially learning the content features of the images by disentangling the unwanted nuisances corresponding to water types (viewed as different domains). We use the learned domain agnostic features to generate enhanced underwater images. We train our model on a dataset consisting images of 10 Jerlov water types. Experimental results show that the proposed model not only outperforms the previous methods in SSIM and PSNR scores for almost all Jerlov water types but also generalizes well on real-world datasets. The performance of a high-level vision task (object detection) also shows improvement using enhanced images with our model.