Swish: Neural Network Cloth Simulation on Madden NFL 21

Abstract

This work presents Swish, a real-time machine-learning based cloth simulation technique for games. Swish was used to generate realistic cloth deformation and wrinkles for NFL player jerseys in Madden NFL 21. To our knowledge, this is the first neural cloth simulation featured in a shipped game. This technique allows accurate high-resolution simulation for tight clothing, which is a case where traditional real-time cloth simulations often achieve poor results. We represent cloth detail using both mesh deformations and a database of normal maps, and train a simple neural network to predict cloth shape from the pose of a character’s skeleton. We share implementation and performance details that will be useful to other practitioners seeking to introduce machine learning into their real-time character pipelines.