Neural reconstruction of 3D ocean wave hydrodynamics from camera sensing
This addresses the need for efficient and accurate wave monitoring in ocean physics, though it is incremental as it builds on existing stereo-vision methods with neural enhancements.
The paper tackles the problem of computationally expensive and occlusion-prone 3D reconstruction of ocean wave hydrodynamics by proposing a neural network that achieves millimetre-level wave elevation prediction, dominant-frequency errors below 0.01 Hz, and dense reconstruction of two million points in 1.35 seconds under real-sea conditions.
Precise three-dimensional (3D) reconstruction of wave free surfaces and associated velocity fields is essential for developing a comprehensive understanding of ocean physics. To address the high computational cost of dense visual reconstruction in long-term ocean wave observation tasks and the challenges introduced by persistent visual occlusions, we propose an wave free surface visual reconstruction neural network, which is designed as an attention-augmented pyramid architecture tailored to the multi-scale and temporally continuous characteristics of wave motions. Using physics-based constraints, we perform time-resolved reconstruction of nonlinear 3D velocity fields from the evolving free-surface boundary. Experiments under real-sea conditions demonstrate millimetre-level wave elevation prediction in the central region, dominant-frequency errors below 0.01 Hz, precise estimation of high-frequency spectral power laws, and high-fidelity 3D reconstruction of nonlinear velocity fields, while enabling dense reconstruction of two million points in only 1.35 s. Built on a stereo-vision dataset, the model outperforms conventional visual reconstruction approaches and maintains strong generalization in occluded conditions, owing to its global multi-scale attention and its learned encoding of wave propagation dynamics.