U2NeRF: Unsupervised Underwater Image Restoration and Neural Radiance Fields
This work addresses underwater image restoration and view synthesis for applications in marine robotics or imaging, presenting an incremental hybrid method.
The paper tackles the problem of restoring underwater images from color shifts and haziness while synthesizing novel views, achieving improvements of up to 11% in LPIPS, 5% in UIQM, and 4% in UCIQE on average compared to baselines.
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.