WaterFlow: Heuristic Normalizing Flow for Underwater Image Enhancement and Beyond

TL;DR

WaterFlow is a novel heuristic normalizing flow model designed for underwater image enhancement that improves visibility and detection performance by incorporating physical priors and semantic guidance.

Contribution

We introduce WaterFlow, a detection-driven invertible mapping method that integrates physical priors and semantic perception for enhanced underwater image quality and detection accuracy.

Findings

Outperforms state-of-the-art methods quantitatively.

Enhances detection performance on underwater images.

Provides credible and interpretable image translation.

Abstract

Underwater images suffer from light refraction and absorption, which impairs visibility and interferes the subsequent applications. Existing underwater image enhancement methods mainly focus on image quality improvement, ignoring the effect on practice. To balance the visual quality and application, we propose a heuristic normalizing flow for detection-driven underwater image enhancement, dubbed WaterFlow. Specifically, we first develop an invertible mapping to achieve the translation between the degraded image and its clear counterpart. Considering the differentiability and interpretability, we incorporate the heuristic prior into the data-driven mapping procedure, where the ambient light and medium transmission coefficient benefit credible generation. Furthermore, we introduce a detection perception module to transmit the implicit semantic guidance into the enhancement procedure, where the enhanced images hold more detection-favorable features and are able to promote the detection performance. Extensive experiments prove the superiority of our WaterFlow, against state-of-the-art methods quantitatively and qualitatively.