SoftSMPL: Data‐driven Modeling of Nonlinear Soft‐tissue Dynamics for Parametric Humans

• Published in: Computer graphics forum Vol. 39; no. 2; pp. 65 - 75
• Main Authors: Santesteban, Igor, Garces, Elena, Otaduy, Miguel A., Casas, Dan
• Format: Journal Article
• Language: English
• Published: Oxford Blackwell Publishing Ltd 01.05.2020
• Subjects: CCS Concepts; Computing methodologies → Animation; Motion capture; Nonlinear dynamics; Training

We present SoftSMPL, a learning‐based method to model realistic soft‐tissue dynamics as a function of body shape and motion. Datasets to learn such task are scarce and expensive to generate, which makes training models prone to overfitting. At the core of our method there are three key contributions...