SpecNeRF: Gaussian Directional Encoding for Specular Reflections

arXiv:2312.13102v2 Announce Type: replace
Abstract: 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 …

3d scenes abstract arxiv cs.cv encoding environment environments fields however lighting map modeling neural radiance fields performance reflections struggle type view