NeuroPump: Simultaneous Geometric and Color Rectification for Underwater Images

TL;DR

NeuroPump is a self-supervised neural method that simultaneously rectifies underwater images' geometry and color distortions by modeling water effects within a Neural Radiance Field framework, enabling better restoration and view synthesis.

Contribution

It introduces a novel approach that jointly addresses geometric and color distortions in underwater images using a NeRF-based model, and provides a new real paired dataset for evaluation.

Findings

Outperforms baseline methods quantitatively and qualitatively

Enables synthesis of novel views and optical effects

Provides a new benchmark dataset with real paired images

Abstract

Underwater image restoration aims to remove geometric and color distortions due to water refraction, absorption and scattering. Previous studies focus on restoring either color or the geometry, but to our best knowledge, not both. However, in practice it may be cumbersome to address the two rectifications one-by-one. In this paper, we propose NeuroPump, a self-supervised method to simultaneously optimize and rectify underwater geometry and color as if water were pumped out. The key idea is to explicitly model refraction, absorption and scattering in Neural Radiance Field (NeRF) pipeline, such that it not only performs simultaneous geometric and color rectification, but also enables to synthesize novel views and optical effects by controlling the decoupled parameters. In addition, to address issue of lack of real paired ground truth images, we propose an underwater 360 benchmark dataset that has real paired (i.e., with and without water) images. Our method clearly outperforms other baselines both quantitatively and qualitatively. Our project page is available at: https://ygswu.github.io/NeuroPump.github.io/.