Learning to Learn and Sample BRDFs

Autor: Liu, Chen, Fischer, Michael, Ritschel, Tobias
Rok vydání: 2022
Předmět:
Druh dokumentu: Working Paper
DOI: 10.1111/cgf.14754
Popis: 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.
Comment: Accepted to Eurographics 2023; Project Page at https://ryushinn.github.io/metasampling
Databáze: arXiv
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje