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

摘要

In this letter, we introduce the idea of AquaFuse, a physics-based method for synthesizing <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">waterbody properties</i> 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 methods, AquaFuse preserves the depth consistency and object geometry in an input scene. We validate this unique feature by comprehensive experiments over diverse sets of underwater scenes. We find that the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">AquaFused images</i> 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.