SoftSMPL: Data-driven Modeling of Nonlinear Soft-tissue Dynamics for Parametric Humans
This work addresses the need for realistic human animation in computer graphics and vision, though it appears incremental as it builds on existing parametric models like SMPL.
The paper tackled the problem of modeling realistic soft-tissue dynamics for parametric humans, which is challenging due to scarce and expensive datasets, and achieved qualitative and quantitative improvements over state-of-the-art methods with better generalization capabilities.
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 that enable us to model highly realistic dynamics and better generalization capabilities than state-of-the-art methods, while training on the same data. First, a novel motion descriptor that disentangles the standard pose representation by removing subject-specific features; second, a neural-network-based recurrent regressor that generalizes to unseen shapes and motions; and third, a highly efficient nonlinear deformation subspace capable of representing soft-tissue deformations of arbitrary shapes. We demonstrate qualitative and quantitative improvements over existing methods and, additionally, we show the robustness of our method on a variety of motion capture databases.