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?

Sourcing data

If you’re working on a deepfake, then you probably already know who you’re going to be swapping. Hopefully, you’re lucky and are working on a deepfake that covers two people who you have access to so you can film them or gather data from them without too much trouble. Unfortunately, not everyone is so lucky, and most of the time, one or both of your subjects will be unavailable for custom data (this is probably why you’re working on a deepfake in the first place, after all).

These two situations require very different approaches to getting data, and sometimes, even if you have good access to your subjects, you will need to get some of your data from another source.

Filming your own data

Filming your own sources is a dream position for any deepfaker. The ability to build the perfect dataset by putting an actor in front of a camera is liberating, but also a wasted opportunity if you don’t know how to capture all that you need...