Asset 12 Asset 10 Asset 11 autodesk_icon_font_1_18_17_start_over-01

Keyboard ALT + g to toggle grid overlay

Michael Mendelson

SD139624-L: Deep Learning Lab: Denoising Rendered Images Using Autoencoders

(Duration 42:43)

  • Save to my AU Saved

Key Learning

Key Learning

  • Learn about noise in rendered images.
  • Learn about the data required to train a neural network to denoise rendering images.
  • Learn to train an autoencoder network to denoise rendered images.
  • Learn to measure the quality of denoising and improve your trained network.

Description

Description

Take your first steps into the world of machine learning. Learn how a neural network can be used to dramatically speed up the removal of noise in ray traced images. In this lab you will learn about noise in rendered images, use a network trained to denoise sample images, and iterate and modify parameters improving the quality of the denoiser. By the end of the lab, you will have the tools and the knowledge to build your own AI accelerated denoiser.

Target Audience

Target Audience

Anyone writing their own ray tracer and is interested in training their own neural network to remove noise from rendered images, Digital content creators who want to learn a concrete example of how AI can be used to improve productivity, Data scientists and developers familiar with deep learning interested in learning about a use case where unsupervised learning creates value

Speakers

Speakers

Michael Mendelson

Mike Mendelson is a Curriculum Designer and Certified Instructor at the Nvidia Deep Learning Institute. Mike began experimenting with deep learning while working to enable active personalized (human) learning. He brings experience building and teaching world class project-based STEM curriculum from Expeditionary Learning Education and is inspired by the power of deep learning to solve some of the world's most important challenges at scale.

Related Classes

Related Classes

Tags

Published

  • 2017
  • SD139624-L
  • AU Las Vegas;

Software

  • Revit
  • 3ds Max
  • VRED
  • Maya

Industry

  • Software Development

Topics

  • Software Development