Domain Adaptation for Underwater Image Enhancement via Content and Style Separation

TL;DR

This paper introduces a domain adaptation framework for underwater image enhancement that separates content and style in latent space, effectively improving enhancement quality on real-world data compared to existing methods.

Contribution

It proposes a novel content-style separation approach in latent space for domain adaptation, enabling better enhancement of real-world underwater images.

Findings

Outperforms state-of-the-art algorithms in quality and quantity.

Effective domain adaptation from synthetic to real underwater images.

Provides user-interactive adjustment of enhancement levels.

Abstract

Underwater image suffer from color cast, low contrast and hazy effect due to light absorption, refraction and scattering, which degraded the high-level application, e.g, object detection and object tracking. Recent learning-based methods demonstrate astonishing performance on underwater image enhancement, however, most of these works use synthetic pair data for supervised learning and ignore the domain gap to real-world data. To solve this problem, we propose a domain adaptation framework for underwater image enhancement via content and style separation, different from prior works of domain adaptation for underwater image enhancement, which target to minimize the latent discrepancy of synthesis and real-world data, we aim to separate encoded feature into content and style latent and distinguish style latent from different domains, i.e. synthesis, real-world underwater and clean domain, and process domain adaptation and image enhancement in latent space. By latent manipulation, our model provide a user interact interface to adjust different enhanced level for continuous change. Experiment on various public real-world underwater benchmarks demonstrate that the proposed framework is capable to perform domain adaptation for underwater image enhancement and outperform various state-of-the-art underwater image enhancement algorithms in quantity and quality. The model and source code will be available at https://github.com/fordevoted/UIESS