Neural BRDF Representation and Importance Sampling
This work addresses the challenge of balancing memory efficiency and rendering fidelity in computer graphics, offering a solution for realistic material representation, though it appears incremental by building on existing neural and analytic methods.
The authors tackled the problem of compressing high-fidelity material appearance data for efficient rendering by developing a neural network-based BRDF representation that achieves high-accuracy reconstruction and enables practical rendering through built-in interpolation, with evaluation showing effective encoding on real-world datasets and importance sampling performance for isotropic BRDFs.
Controlled capture of real-world material appearance yields tabulated sets of highly realistic reflectance data. In practice, however, its high memory footprint requires compressing into a representation that can be used efficiently in rendering while remaining faithful to the original. Previous works in appearance encoding often prioritised one of these requirements at the expense of the other, by either applying high-fidelity array compression strategies not suited for efficient queries during rendering, or by fitting a compact analytic model that lacks expressiveness. We present a compact neural network-based representation of BRDF data that combines high-accuracy reconstruction with efficient practical rendering via built-in interpolation of reflectance. We encode BRDFs as lightweight networks, and propose a training scheme with adaptive angular sampling, critical for the accurate reconstruction of specular highlights. Additionally, we propose a novel approach to make our representation amenable to importance sampling: rather than inverting the trained networks, we learn to encode them in a more compact embedding that can be mapped to parameters of an analytic BRDF for which importance sampling is known. We evaluate encoding results on isotropic and anisotropic BRDFs from multiple real-world datasets, and importance sampling performance for isotropic BRDFs mapped to two different analytic models.