Tg, ThomsonTran, Duc MinhJensen, Henrik W.Ramamoorthi, RaviFrisvad, Jeppe RevallGarces, ElenaHaines, Eric2024-06-252024-06-2520241467-8659https://doi.org/10.1111/cgf.15158https://diglib.eg.org/handle/10.1111/cgf15158We present a method for capturing the BSSRDF (bidirectional scattering-surface reflectance distribution function) of arbitrary geometry with a neural network. We demonstrate how a compact neural network can represent the full 8-dimensional light transport within an object including heterogeneous scattering. We develop an efficient rendering method using importance sampling that is able to render complex translucent objects under arbitrary lighting. Our method can also leverage the common planar half-space assumption, which allows it to represent one BSSRDF model that can be used across a variety of geometries. Our results demonstrate that we can render heterogeneous translucent objects under arbitrary lighting and obtain results that match the reference rendered using volumetric path tracing.Attribution 4.0 International LicenseCCS Concepts: Computing methodologies → Reflectance modeling; Neural networksComputing methodologies → Reflectance modelingNeural networks10.1111/cgf.1515814 pages