Gaussian Material Synthesis

TL;DR

This paper introduces a learning-based system that rapidly synthesizes high-quality materials using Gaussian Process Regression and neural networks, significantly improving workflow efficiency for both novices and experts in material modeling.

Contribution

The paper presents a novel real-time material synthesis system combining Gaussian Process Regression and neural networks to accelerate and simplify the creation of high-quality materials.

Findings

Neural network predicts materials in real time, replacing slow rendering.

System scales well with the number of materials, aiding rapid modeling.

Enables real-time fine-tuning of materials without domain expertise.

Abstract

We present a learning-based system for rapid mass-scale material synthesis that is useful for novice and expert users alike. The user preferences are learned via Gaussian Process Regression and can be easily sampled for new recommendations. Typically, each recommendation takes 40-60 seconds to render with global illumination, which makes this process impracticable for real-world workflows. Our neural network eliminates this bottleneck by providing high-quality image predictions in real time, after which it is possible to pick the desired materials from a gallery and assign them to a scene in an intuitive manner. Workflow timings against Disney's "principled" shader reveal that our system scales well with the number of sought materials, thus empowering even novice users to generate hundreds of high-quality material models without any expertise in material modeling. Similarly, expert users experience a significant decrease in the total modeling time when populating a scene with materials. Furthermore, our proposed solution also offers controllable recommendations and a novel latent space variant generation step to enable the real-time fine-tuning of materials without requiring any domain expertise.