ShinyNeRF: Modeling Anisotropic Reflections in Neural Radiance Fields

Recent advances in digitization technologies have transformed the preservation and dissemination of cultural heritage. In this vein, neural Radiance Fields (NeRF) have emerged as a leading technology for 3D digitization, delivering representations with exceptional realism. However, existing methods struggle to model anisotropic specular surfaces (like brushed metals). In this work, we introduce ShinyNeRF, a novel framework capable of handling both isotropic and anisotropic reflections. Our method is capable to jointly estimate surface normals, tangents, specular concentration, and anisotropy magnitudes of an Anisotropic Spherical Gaussian (ASG) distribution, by learning an approximation of the outgoing radiance as an encoded set of isotropic von Mises-Fisher (vMF) distributions. Experimental results show that ShinyNeRF achieves state-of-the-art performance and offers plausible physical interpretations and editing compared to existing methods.