Publications

A Reduced-Precision Network for Image Reconstruction [2020]

We present QW-Net, a novel 4-bit quantized network that performs temporally amortized supersampling for high-dynamic-range rendering.

Learning Patterns in Sample Distributions for Monte Carlo Variance Reduction [2019]

We visualize – and use artificial neural networks to learn – the shapes of statistical sample distributions in Monte Carlo rendering, and apply that knowledge to produce improved (denoised) images from small sample sets.
Learning Patterns in Sample Distributions for Monte Carlo Variance Reduction [2019]

Deep Illumination: Approximating Dynamic Global Illumination with Generative Adversarial Network [2017]

We present Deep Illumination, a novel machine learning technique for approximating global illumination (GI) in real-time applications using a Conditional Generative Adversarial Network.
Deep Illumination: Approximating Dynamic Global Illumination with Generative Adversarial Network [2017]