SpecNeRF: Gaussian Directional Encoding for Specular Reflections
This addresses the issue of view-dependent appearance for glossy surfaces in 3D scene modeling, which is incremental as it builds on existing NeRF methods.
The paper tackled the problem of modeling specular reflections in neural radiance fields under near-field lighting, proposing a Gaussian directional encoding and geometry prior that improved performance in challenging indoor environments.
Neural radiance fields have achieved remarkable performance in modeling the appearance of 3D scenes. However, existing approaches still struggle with the view-dependent appearance of glossy surfaces, especially under complex lighting of indoor environments. Unlike existing methods, which typically assume distant lighting like an environment map, we propose a learnable Gaussian directional encoding to better model the view-dependent effects under near-field lighting conditions. Importantly, our new directional encoding captures the spatially-varying nature of near-field lighting and emulates the behavior of prefiltered environment maps. As a result, it enables the efficient evaluation of preconvolved specular color at any 3D location with varying roughness coefficients. We further introduce a data-driven geometry prior that helps alleviate the shape radiance ambiguity in reflection modeling. We show that our Gaussian directional encoding and geometry prior significantly improve the modeling of challenging specular reflections in neural radiance fields, which helps decompose appearance into more physically meaningful components.