1 University College London
2 Imperial College London
3 Ecole Polytechnique Fédérale de Lausanne (EPFL)
Realistic rendering using sets of discrete reflectance measurements is challenging, because any directions on the light and view hemispheres could be queried at render time. This motivates the need for continuous parametrizations and models akin to analytic BRDFs; however, fitting BRDF parameters to complex data such as BTF texels can prove challenging, as models tend to describe restricted function spaces that cannot encompass real-world behavior. Recent advances in this area have increasingly relied on neural representations that are trained to reproduce acquired 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 projects reflectance measurements to a shared latent parameter space. Similarly to SVBRDF fitting, real-world materials are mapped to a set of parameters, and the decoder network is analog to the analytic BRDF expression (also parameterized on light and view directions for practical rendering application). With this approach, encoding materials becomes a simple matter of evaluating the network. We train and validate on BTF datasets of the University of Bonn, but there are no prerequisites on either the number of angular reflectance samples, or the sample positions. Additionally, we show that the latent space is well-behaved and can be sampled from, for applications such as mipmapping and texture synthesis.
Gilles Rainer, Abhijeet Ghosh, Wenzel Jakob, Tim Weyrich.
Conditionally accepted to Computer Graphics Forum (Proc. Eurographics), 39(2), 12 pages, 2020.Gilles Rainer, Abhijeet Ghosh, Wenzel Jakob, and Tim Weyrich. Unified neural encoding of BTFs. Computer Graphics Forum (Proc. Eurographics), conditionally accepted, 39(2):1–12, 2020.Rainer, G., Ghosh, A., Jakob, W., and Weyrich, T. 2020. Unified neural encoding of BTFs. Computer Graphics Forum (Proc. Eurographics), conditionally accepted 39, 2, 1–12.G. Rainer, A. Ghosh, W. Jakob, and T. Weyrich, “Unified neural encoding of BTFs,” Computer Graphics Forum (Proc. Eurographics), conditionally accepted, vol. 39, no. 2, pp. 1–12, 2020.