U2NeRF: Unsupervised Underwater Image Restoration and Neural Radiance Fields

TL;DR

U2NeRF is an unsupervised, transformer-based neural radiance field model that restores and renders underwater images and views by disentangling scene components, outperforming baselines on a new underwater dataset.

Contribution

The paper introduces U2NeRF, a novel unsupervised neural radiance field architecture for underwater image restoration and view synthesis, with a new dataset and improved performance.

Findings

U2NeRF outperforms baselines in image quality metrics.

It effectively disentangles scene radiance and transmission components.

Demonstrates superior rendering and restoration on underwater scenes.

Abstract

Underwater images suffer from colour shifts, low contrast, and haziness due to light absorption, refraction, scattering and restoring these images has warranted much attention. In this work, we present Unsupervised Underwater Neural Radiance Field U2NeRF, a transformer-based architecture that learns to render and restore novel views conditioned on multi-view geometry simultaneously. Due to the absence of supervision, we attempt to implicitly bake restoring capabilities onto the NeRF pipeline and disentangle the predicted color into several components - scene radiance, direct transmission map, backscatter transmission map, and global background light, and when combined reconstruct the underwater image in a self-supervised manner. In addition, we release an Underwater View Synthesis UVS dataset consisting of 12 underwater scenes, containing both synthetically-generated and real-world data. Our experiments demonstrate that when optimized on a single scene, U2NeRF outperforms several baselines by as much LPIPS 11%, UIQM 5%, UCIQE 4% (on average) and showcases improved rendering and restoration capabilities. Code will be made available upon acceptance.