“Swish: Neural Network Cloth Simulation on Madden NFL 21” by Lewin, Power and Cobb

  • ©Chris Lewin, James Power, and James Cobb



Entry Number: 39


    Swish: Neural Network Cloth Simulation on Madden NFL 21



    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.


    Daniel Holden, Bang Chi Duong, Sayantan Datta, and Derek Nowrouzezahrai. 2019. Subspace Neural Physics: Fast Data-Driven Interactive Simulation. In Proceedings of the 18th Annual ACM SIGGRAPH/Eurographics Symposium on Computer Animation (Los Angeles, California) (SCA ’19).

    Paul G. Kry, Doug L. James, and Dinesh K. Pai. 2002. EigenSkin: Real Time Large Deformation Character Skinning in Hardware. In Proceedings of the 2002 ACM SIGGRAPH/Eurographics Symposium on Computer Animation (San Antonio, Texas) (SCA ’02). Association for Computing Machinery, New York, NY, USA, 153–159. https://doi.org/10.1145/545261.545286

    Matthias Müller, Bruno Heidelberger, Marcus Hennix, and John Ratcliff. 2007. Position Based Dynamics. J. Vis. Comun. Image Represent. 18, 2 (April 2007), 109–118.

    Yi Zhou, Connelly Barnes, Jingwan Lu, Jimei Yang, and Hao Li. 2020. On the Continuity of Rotation Representations in Neural Networks. arXiv:1812.07035 [cs.LG]


ACM Digital Library Publication: