NeReF: Neural Refractive Field for Fluid Surface Reconstruction and Implicit Representation
This work addresses a specific bottleneck in computer vision for fluid analysis, offering a novel method but is incremental in extending neural fields to transparent materials.
The paper tackles the problem of reconstructing transparent fluid surfaces, which is challenging for existing neural methods like NeRF that focus on opaque objects, and demonstrates that NeReF achieves high-fidelity reconstruction, particularly with sparse multi-view data.
Existing neural reconstruction schemes such as Neural Radiance Field (NeRF) are largely focused on modeling opaque objects. We present a novel neural refractive field(NeReF) to recover wavefront of transparent fluids by simultaneously estimating the surface position and normal of the fluid front. Unlike prior arts that treat the reconstruction target as a single layer of the surface, NeReF is specifically formulated to recover a volumetric normal field with its corresponding density field. A query ray will be refracted by NeReF according to its accumulated refractive point and normal, and we employ the correspondences and uniqueness of refracted ray for NeReF optimization. We show NeReF, as a global optimization scheme, can more robustly tackle refraction distortions detrimental to traditional methods for correspondence matching. Furthermore, the continuous NeReF representation of wavefront enables view synthesis as well as normal integration. We validate our approach on both synthetic and real data and show it is particularly suitable for sparse multi-view acquisition. We hence build a small light field array and experiment on various surface shapes to demonstrate high fidelity NeReF reconstruction.