Research Output
MienCap: Performance-based Facial Animation with Live Mood Dynamics
  Our purpose is to improve performance-based animation which can drive believable 3D stylized characters that are truly perceptual. By combining traditional blendshape animation techniques with machine learning models, we present a real time motion capture system, called MienCap, which drive character expressions in a geometrically consistent and perceptually valid way. We demon-strate the effectiveness of our system by comparing to a commercial product Faceware. Results reveal that ratings of the recognition of expressions depicted for animated characters via our systems are statistically higher than Faceware. Our results may be implemented into the VR filmmaking and animation pipeline, and provide animators with a system for creating the expressions they wish to use more quickly and accurately.

  • Date:

    31 March 2022

  • Publication Status:

    Published

  • Publisher

    IEEE

  • DOI:

    10.1109/vrw55335.2022.00178

  • Cross Ref:

    10.1109/vrw55335.2022.00178

  • Funders:

    Edinburgh Napier Funded

Citation

Pan, Y., Zhang, R., Wang, J., Chen, N., Qiu, Y., Ding, Y., & Mitchell, K. (2022). MienCap: Performance-based Facial Animation with Live Mood Dynamics. In 2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW) (645-646). https://doi.org/10.1109/vrw55335.2022.00178

Authors

Monthly Views:

Available Documents