“FaceBaker: Baking Character Facial Rigs with Machine Learning” by Radzihovsky, Goes and Meyer

  • ©Sarah Radzihovsky, Fernando de Goes, and Mark Meyer

  • ©Sarah Radzihovsky, Fernando de Goes, and Mark Meyer

  • ©Sarah Radzihovsky, Fernando de Goes, and Mark Meyer

Conference:


Entry Number: 58

Title:

    FaceBaker: Baking Character Facial Rigs with Machine Learning

Presenter(s):



Abstract:


    Character rigs are procedural systems that deform a character’s shape driven by a set of rig-control variables. Film quality character rigs are highly complex and therefore computationally expensive and slow to evaluate. We present a machine learning method for approximating facial mesh deformations which reduces rig computations, increases longevity of characters without rig upkeep, and enables portability of proprietary rigs into a variety of external platforms. We perform qualitative and quantitative evaluations on hero characters across several feature films, exhibiting the speed and generality of our approach and demonstrating that our method outperforms existing state-of-the-art work on deformation approximations for character faces.

References:


    Stephen W. Bailey, Dave Otte, Paul Dilorenzo, and James F. O’Brien. 2018. Fast and Deep Deformation Approximations. ACM Transactions on Graphics 37, 4 (Aug. 2018). https://doi.org/10.1145/3197517.3201300

    Paul Kanyuk, Patrick Coleman, and Jonah Laird. 2018. Mobilizing Mocap, Motion Blending, and Mayhem: Rig Interoperability for Crowd Simulation on Incredibles 2. In ACM SIGGRAPH 2018 Talks (SIGGRAPH ’18). Article Article 51, 2 pages.


PDF:



ACM Digital Library Publication:



Overview Page:


Type: