MaterialGAN: Reflectance Capture using a Generative SVBRDF Model

TL;DR

MaterialGAN leverages a StyleGAN2-based deep generative model to accurately reconstruct spatially-varying BRDFs from limited images, enabling realistic material synthesis, editing, and improved inverse rendering performance.

Contribution

We introduce MaterialGAN, a novel deep generative model for SVBRDFs that enhances inverse rendering and enables semantic material editing from minimal image data.

Findings

Outperforms previous methods in SVBRDF reconstruction accuracy.

Successfully reconstructs plausible materials from images captured with a mobile phone.

Enables high-level semantic editing of materials through the GAN latent space.

Abstract

We address the problem of reconstructing spatially-varying BRDFs from a small set of image measurements. This is a fundamentally under-constrained problem, and previous work has relied on using various regularization priors or on capturing many images to produce plausible results. In this work, we present MaterialGAN, a deep generative convolutional network based on StyleGAN2, trained to synthesize realistic SVBRDF parameter maps. We show that MaterialGAN can be used as a powerful material prior in an inverse rendering framework: we optimize in its latent representation to generate material maps that match the appearance of the captured images when rendered. We demonstrate this framework on the task of reconstructing SVBRDFs from images captured under flash illumination using a hand-held mobile phone. Our method succeeds in producing plausible material maps that accurately reproduce the target images, and outperforms previous state-of-the-art material capture methods in evaluations on both synthetic and real data. Furthermore, our GAN-based latent space allows for high-level semantic material editing operations such as generating material variations and material morphing.