“Simulation-aided face strain extraction for ML animation systems” by Klár, Ward, Moffat, Sifakis and Museth – ACM SIGGRAPH HISTORY ARCHIVES

“Simulation-aided face strain extraction for ML animation systems” by Klár, Ward, Moffat, Sifakis and Museth

  • ©

Conference:


Type(s):


Interest Area:


    Production & Animation

Title:

    Simulation-aided face strain extraction for ML animation systems

Session/Category Title:   Big Rigs: Advances in Rigging


Presenter(s)/Author(s):



Abstract:


    We present a volumetric, simulation-based pipeline for the automatic creation of strain-based descriptors from facial performance capture provided as surface meshes. Strain descriptors encode facial poses via length elongation/contraction ratios of curves embedded in the flesh volume. Strains are anatomically motivated, correlate strongly to muscle action, and offer excellent coverage of the pose space. Our proposed framework extracts such descriptors from surface-only performance capture data, by extrapolating this deformation into the flesh volume in a physics-based fashion that respects collisions and filters non-physical capture defects. The result of our system feeds into Machine Learning facial animation tools, as employed in Avatar: The Way of Water.

References:


    [1] B. Choi, H. Eom, B. Mouscadet, S. Cullingford, K. Ma, S. Gassel, S. Kim, A. Moffat, M. Maier, M. Revelant, J. Letteri, and K. Singh. 2022. Animatomy: An Animator-Centric, Anatomically Inspired System for 3D Facial Modeling, Animation and Transfer. In SIGGRAPH Asia 2022 Conference Papers(SA ’22). Article 16, 9 pages.
    [2] G. Klár, A. Moffat, K. Museth, and E. Sifakis. 2020. Shape Targeting: A Versatile Active Elasticity Constitutive Model. In ACM SIGGRAPH 2020 Talks. Association for Computing Machinery, New York, NY, USA, Article 59, 2 pages.

ACM Digital Library Publication:



Overview Page:



Submit a story:

If you would like to submit a story about this presentation, please contact us: historyarchives@siggraph.org