Skip to main content Skip to main navigation

Publication

Motion Data and Model Management for Applied Statistical Motion Synthesis

Erik Herrmann; Han Du; André Antakli; Dmitri Rubinstein; René Schubotz; Janis Sprenger; Somayeh Hosseini; Noshaba Cheema; Ingo Zinnikus; Martin Manns; Klaus Fischer; Philipp Slusallek
In: Marco Agus; Massimiliano Corsini; Ruggero Pintus (Hrsg.). Smart Tools and Applications in Computer Graphics 2019. Smart Tools and Applications in Computer Graphics (STAG-2019), November 14-15, Cagliari, Sardinia, Italy, Pages 79-88, ISBN 978-3-03868-100-7, The Eurographics Association, 11/2019.

Abstract

Machine learning based motion modelling methods such as statistical modelling require a large amount of input data. In practice, the management of the data can become a problem in itself for artists who want to control the quality of the motion models. As a solution to this problem, we present a motion data and model management system and integrate it with a statistical motion modelling pipeline. The system is based on a data storage server with a REST interface that enables the efficient storage of different versions of motion data and models. The database system is combined with a motion preprocessing tool that provides functions for batch editing, retargeting and annotation of the data. For the application of the motion models in a game engine, the framework provides a stateful motion synthesis server that can load the models directly from the data storage server. Additionally, the framework makes use of a Kubernetes compute cluster to execute time consuming processes such as the preprocessing and modelling of the data. The system is evaluated in a use case for the simulation of manual assembly workers.

Projekte

Weitere Links