HIFI-Net: A Novel Network for Enhancement to Underwater Images

TL;DR

HIFI-Net is a new neural network designed to enhance underwater images by fusing original images with important information using a Reinforcement Fusion Module, outperforming existing methods on multiple datasets.

Contribution

Introduces HIFI-Net, a novel network utilizing Reinforcement Fusion Module for improved underwater image enhancement through Haar wavelet image fusion.

Findings

HIFI-Net outperforms state-of-the-art methods on three datasets.

Achieves top results on multiple evaluation metrics.

Demonstrates effectiveness of Haar wavelet fusion in image enhancement.

Abstract

A novel network for enhancement to underwater images is proposed in this paper. It contains a Reinforcement Fusion Module for Haar wavelet images (RFM-Haar) based on Reinforcement Fusion Unit (RFU), which is used to fuse an original image and some important information within it. Fusion is achieved for better enhancement. As this network make "Haar Images into Fusion Images", it is called HIFI-Net. The experimental results show the proposed HIFI-Net performs best among many state-of-the-art methods on three datasets at three normal metrics and a new metric.