Manu Mathew Thomas

University of California, Santa Cruz

About

I’m a PhD student in the Creative Coding Lab at the University of California at Santa Cruz, advised by Prof. Angus Forbes. My research focuses on solving various 3D rendering problems with deep learning solutions optimized for high performance. Feel free contact me via email: manumathewthomas (at) gmail (dot) com

Interests

Computer Graphics
Machine Learning
Visualization

Education

PhD in Computational Media (2018-)
University of California, Santa Cruz
MS in Computer Science (2015-2018)
University of Illinois at Chicago
BTech in Computer Science (2008-2012)
Cochin University of Science and Technology

Selected 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.

Manu Mathew Thomas, Karthik Vaidyanathan, Gabor Liktor, and Angus G. Forbes

Project

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.

Oskar Elek Manu M. Thomas Angus Forbes

PDF

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.

Manu Thomas, Angus G Forbes

PDF

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