Neural BRDF Representation and Importance Sampling

02/11/2021
by   Alejandro Sztrajman, et al.
9

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.

READ FULL TEXT

page 3

page 4

page 5

page 6

page 8

page 9

research
06/21/2022

An attempt to trace the birth of importance sampling

In this note, we try to trace the birth of importance sampling (IS) back...
research
11/22/2019

Importance Sampling of Many Lights with Reinforcement Lightcuts Learning

In this manuscript, we introduce a novel technique for sampling and inte...
research
10/25/2022

BSDF Importance Baking: A Lightweight Neural Solution to Importance Sampling General Parametric BSDFs

Parametric Bidirectional Scattering Distribution Functions (BSDFs) are p...
research
05/04/2023

Real-Time Neural Appearance Models

We present a complete system for real-time rendering of scenes with comp...
research
07/21/2023

Tri-MipRF: Tri-Mip Representation for Efficient Anti-Aliasing Neural Radiance Fields

Despite the tremendous progress in neural radiance fields (NeRF), we sti...
research
03/11/2023

Online Neural Path Guiding with Normalized Anisotropic Spherical Gaussians

The variance reduction speed of physically-based rendering is heavily af...
research
09/07/2021

Optimizing model-agnostic Random Subspace ensembles

This paper presents a model-agnostic ensemble approach for supervised le...

Please sign up or login with your details

Forgot password? Click here to reset