AquaFuse: Waterbody Fusion for Physics Guided View Synthesis of Underwater Scenes

TL;DR

AquaFuse is a physics-based method for realistic underwater scene synthesis that preserves depth and geometry, enabling improved data augmentation and view synthesis for underwater imaging.

Contribution

It introduces a closed-form waterbody fusion technique that maintains depth and object geometry, advancing underwater scene rendering beyond data-driven style transfer.

Findings

Preserves over 94% depth consistency

Maintains 90-95% structural similarity

Enables accurate 3D view synthesis

Abstract

We introduce the idea of AquaFuse, a physics-based method for synthesizing waterbody properties in underwater imagery. We formulate a closed-form solution for waterbody fusion that facilitates realistic data augmentation and geometrically consistent underwater scene rendering. AquaFuse leverages the physical characteristics of light propagation underwater to synthesize the waterbody from one scene to the object contents of another. Unlike data-driven style transfer, AquaFuse preserves the depth consistency and object geometry in an input scene. We validate this unique feature by comprehensive experiments over diverse underwater scenes. We find that the AquaFused images preserve over 94% depth consistency and 90-95% structural similarity of the input scenes. We also demonstrate that it generates accurate 3D view synthesis by preserving object geometry while adapting to the inherent waterbody fusion process. AquaFuse opens up a new research direction in data augmentation by geometry-preserving style transfer for underwater imaging and robot vision applications.