Performance capture is about bringing digital characters to life by capturing the geometry and motion of real human performances.
Our research covers the full pipeline for data-driven modeling and animation of virtual avatars, which includes real-time markerless acquisition, tracking in non-rigid partial data, deformable shape completion, motion-retargeting, and automatic character rigging.
Low-Dimensionality Calibration through Local Anisotropic Scaling for Robust Hand Model Personalization2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, Octobre 22-29, 2017.
Online modeling for real-time facial animation
US2023024768; US11348299; EP3518184; US2020160582; US10586372; AU2014277220; CN110310349; EP3518184; CN105900144; US2019156549; EP3005302; US10192343; US2017301125; US9734617; US2016350958; CN105900144; US9378576; AU2014277220; EP3005302; US2014362091; WO2014195018.2016.