MAC-Lookup: Multi-Axis Conditional Lookup Model for Underwater Image Enhancement

TL;DR

MAC-Lookup is a novel deep learning model that significantly improves underwater image quality by effectively restoring colors, details, and contrast, overcoming limitations of traditional and existing deep learning methods.

Contribution

The paper introduces MAC-Lookup, a new multi-axis conditional lookup model with specialized modules for color correction and adaptive enhancement tailored for underwater images.

Findings

Outperforms existing methods in color accuracy and detail restoration

Effectively prevents over-enhancement and saturation issues

Demonstrates superior visual quality in extensive experiments

Abstract

Enhancing underwater images is crucial for exploration. These images face visibility and color issues due to light changes, water turbidity, and bubbles. Traditional prior-based methods and pixel-based methods often fail, while deep learning lacks sufficient high-quality datasets. We introduce the Multi-Axis Conditional Lookup (MAC-Lookup) model, which enhances visual quality by improving color accuracy, sharpness, and contrast. It includes Conditional 3D Lookup Table Color Correction (CLTCC) for preliminary color and quality correction and Multi-Axis Adaptive Enhancement (MAAE) for detail refinement. This model prevents over-enhancement and saturation while handling underwater challenges. Extensive experiments show that MAC-Lookup excels in enhancing underwater images by restoring details and colors better than existing methods. The code is https://github.com/onlycatdoraemon/MAC-Lookup.