Towards Underwater Image Restoration: A Physical-accurate Pipeline and a Large Scale Full-reference Benchmark

Jiayan Tong1, Lin Zhang2,*, Tianjun Zhang2

1 School of Electronic and Information Engineering, Tongji University, Shanghai, China

2 School of Software Engineering, Tongji University, Shanghai, China

Introduction

This is the website for our paper "Towards Underwater Image Restoration: A Physical-accurate Pipeline and a Large Scale Full-reference Benchmark, International Conference on Multimedia and Expo, 2022"

Abstract

Underwater images always present low-quality features such as low contrast, blurred edges and color distortion, which brings great challenges to high-level underwater vision tasks. In this paper, a novel underwater image restoration method, namely MonoUIR (Monocular Underwater Image Restoration), is proposed, which is based on a more physical-accurate imaging model compared to existing schemes. And with the monocular depth estimation, MonoUIR has no dependence on extra ranging equipment or specific shooting operations. Experimental results demonstrate that MonoUIR overwhelmingly outperforms other physical model-based competitors. In addition, the Real-world Undersea Color Board (RUCB) dataset is established, providing the ill-conditioned underwater images collected in the East China Sea and the corresponding high-quality references. To our knowledge, this is the first full-reference underwater benchmark dataset collected entirely in a real-world marine environment, which will further support the full-reference evaluation of underwater image restoration approaches.

Source Codes

Get the code

Use git to clone the repository:

    git clone git@github.com:TongJiayan/MonoUIR.git

Dataset

RUCB-dataset 提取码: 6cf0

Demo Video

The following is the demo video of underwater image restoration using our MonoUIR.

Last update: Mar. 27, 2022