2020
DGAN: Disentangled Representation Learning for Anisotropic BRDF Reconstruction
ICASSP 2020accepted
Accurate reconstruction of real-world materials' appearance from a very limited number of samples is still a huge challenge in computer vision and graphics. In this paper, we present a novel deep architecture, Disentangled Generative Adversarial Network (DGAN), which performs anisotropic Bidirection…