Book Image

Exploring Deepfakes

By : Bryan Lyon, Matt Tora
Book Image

Exploring Deepfakes

By: Bryan Lyon, Matt Tora

Overview of this book

Applying Deepfakes will allow you to tackle a wide range of scenarios creatively. Learning from experienced authors will help you to intuitively understand what is going on inside the model. You’ll learn what deepfakes are and what makes them different from other machine learning techniques, and understand the entire process from beginning to end, from finding faces to preparing them, training the model, and performing the final swap. We’ll discuss various uses for face replacement before we begin building our own pipeline. Spending some extra time thinking about how you collect your input data can make a huge difference to the quality of the final video. We look at the importance of this data and guide you with simple concepts to understand what your data needs to really be successful. No discussion of deepfakes can avoid discussing the controversial, unethical uses for which the technology initially became known. We’ll go over some potential issues, and talk about the value that deepfakes can bring to a variety of educational and artistic use cases, from video game avatars to filmmaking. By the end of the book, you’ll understand what deepfakes are, how they work at a fundamental level, and how to apply those techniques to your own needs.
Table of Contents (15 chapters)
1
Part 1: Understanding Deepfakes
6
Part 2: Getting Hands-On with the Deepfake Process
10
Part 3: Where to Now?

Improving your data

There are no silver bullets to magically make your data better, but there are some ways that you can tweak your data to improve the training of the AI.

Linear color

When you’re filming you may film in logarithmic scale (log) color, where the scale represents an exponential change. This is great for storing a large color range while filming but does not work well for training a deepfake. To get the best results from your training, you’ll want to convert your video into a linear color space (where a change of some number is consistently represented). It doesn’t really matter which one, but all your data and converted videos should be the same. Since most content is Rec.709, we recommend that you use that unless you have a good reason to pick a different color space.

Author’s note

Color science is a very robust field, and a full examination is outside the scope of this book. However, a basic understanding can help. Rec.709 is...