Learning to Learn and Sample BRDFs

TL;DR

This paper introduces a meta-learning approach that accelerates both the physical acquisition and neural learning of BRDF models, significantly reducing the number of samples needed for new BRDFs while maintaining quality.

Contribution

It extends meta-learning to optimize physical sampling patterns for BRDF acquisition, enabling rapid learning with fewer samples across various models.

Findings

Achieves up to five orders of magnitude reduction in physical samples needed.

Works effectively on both linear and non-linear BRDF models.

Maintains high-quality BRDF reconstructions with fewer samples.

Abstract

We propose a method to accelerate the joint process of physically acquiring and learning neural Bi-directional Reflectance Distribution Function (BRDF) models. While BRDF learning alone can be accelerated by meta-learning, acquisition remains slow as it relies on a mechanical process. We show that meta-learning can be extended to optimize the physical sampling pattern, too. After our method has been meta-trained for a set of fully-sampled BRDFs, it is able to quickly train on new BRDFs with up to five orders of magnitude fewer physical acquisition samples at similar quality. Our approach also extends to other linear and non-linear BRDF models, which we show in an extensive evaluation.