Skip to Main content Skip to Navigation
Journal articles

DSNet: Dynamic Skin Deformation Prediction by Recurrent Neural Network

Abstract : Skin dynamics contributes to the enriched realism of human body models in rendered scenes. Traditional methods rely on physics-based simulations to accurately reproduce the dynamic behavior of soft tissues. Due to the model complexity and thus the heavy computation, however, they do not directly offer practical solutions to domains where real-time performance is desirable. The quality shapes obtained by physics-based simulations are not fully exploited by example-based or more recent datadriven methods neither, with most of them having focused on the modeling of static skin shapes by leveraging quality data. To address these limitations, we present a learningbased method for dynamic skin deformation. At the core of our work is a recurrent neural network that learns to predict the nonlinear, dynamics-dependent shape change over time from pre-existing mesh deformation sequence data. Our network also learns to predict the variation of skin dynamics across different individuals with varying body shapes. After training the network delivers realistic, high-quality skin dynamics that is specific to a person in a real-time course. We obtain results that significantly saves the computational time, while maintaining comparable prediction quality compared to state-of-the-art results.
Complete list of metadata
Contributor : Hyewon Seo Connect in order to contact the contributor
Submitted on : Friday, November 26, 2021 - 10:18:28 AM
Last modification on : Wednesday, December 1, 2021 - 3:32:13 PM


Files produced by the author(s)



Hyewon Seo, Kaifeng Zou, Frederic Cordier. DSNet: Dynamic Skin Deformation Prediction by Recurrent Neural Network. Lecture Notes in Computer Science, Springer, 2021, Lecture Notes in Computer Science, 13002, pp.365-377. ⟨10.1007/978-3-030-89029-2_29⟩. ⟨hal-03450610⟩



Les métriques sont temporairement indisponibles