Unified neural encoding of BTFs

Abstract

Realistic rendering using discrete reflectance measurements is challenging, because arbitrary directions on the light and viewhemispheres are queried at render time, incurring large memory requirements and the need for interpolation. This explains thedesire for compact and continuously parametrized models akin to analytic BRDFs; however, fitting BRDF parameters to complexdata such as BTF texels can prove challenging, as models tend to describe restricted function spaces that cannot encompassreal-world behavior. Recent advances in this area have increasingly relied on neural representations that are trained to reproduceacquired reflectance data. The associated training process is extremely costly and must typically be repeated for each material.Inspired by autoencoders, we propose a unified network architecture that is trained on a variety of materials, and which projectsreflectance measurements to a shared latent parameter space. Similarly to SVBRDF fitting, real-world materials are representedby parameter maps, and the decoder network is analog to the analytic BRDF expression (also parametrized on light and viewdirections for practical rendering application). With this approach, encoding and decoding materials becomes a simple matter ofevaluating the network. We train and validate on BTF datasets of the University of Bonn, but there are no prerequisites on eitherthe number of angular reflectance samples, or the sample positions. Additionally, we show that the latent space is well-behavedand can be sampled from, for applications such as mipmapping and texture synthesis.