rishabh battulwar
play

Rishabh Battulwar Research and Development at Digital Domain VFx - PowerPoint PPT Presentation

Data-Driven Future in Visual Effects Rishabh Battulwar Research and Development at Digital Domain VFx pipelines Fluids Hair Smoke Fire Rigid Body Facial Animation What s important? Natural Facial Shapes Realistic Appearance Facial


  1. Data-Driven Future in Visual Effects Rishabh Battulwar Research and Development at Digital Domain

  2. VFx pipelines Fluids Hair Smoke Fire Rigid Body

  3. Facial Animation What ’ s important? Natural Facial Shapes Realistic Appearance

  4. Facial Motion Highly Non-Linear Organic Person Specific

  5. Facial Animation Goal

  6. Traditional Model Facial Action Coding System (FACS) Codify Facial Expressions Inspired by Facial Musculature GENERIC Facial Shape Basis* Ekman and Friesen (1978) Empirical Interpretations 50-60 Primary Shapes

  7. FACS Model 50-60 Primary Shapes More than 1000 Combination Shapes Animation Rig Setup FACS shapes

  8. FACS Model An example of combination shape in FACS model 50-60 Primary Shapes Primary Shape Primary Shape Hand-CORRECTED Combo Shape More than 1000 Combination Shapes [A+B]* [A] [B]

  9. FACS Model 50-60 Primary Shapes More than 1000 Combination Shapes Animation Rig Setup FACS shapes

  10. FACS Model FACS based process

  11. Geometric Approach Low-Resolution Capture

  12. Geometric Approach MASQUERADE Geometric Mesh Deformer Output

  13. Geometric Approach Correspondence Mapping Performance Transfer using Differential Geometry

  14. Geometric Approach Quick Result ! MASQUERADE Geometric Mesh Deformer Output

  15. Geometric Approach Quick Result ! NO ! Medium-scale & Hi-resolution detail ! NOT ! True to the Person MASQUERADE Geometric Mesh Deformer Output

  16. NO ! NOT ! Medium-scale & True to the Person Hi-resolution detail !

  17. NO ! NOT ! Medium-scale & True to the Person Hi-resolution detail !

  18. NO ! NOT ! Medium-scale & True to the Person Hi-resolution detail !

  19. Data Preparation Raw Data Capture Rigs

  20. Data Preparation Capturing Facial Range of Motion Offline Processing High-Resolution Captures

  21. Data Preparation Capturing Mesoscopic Detail Texture Maps More High-Resolution Captures

  22. Data-driven Shape Model Taking sparse facial capture to high-resolution data Moser et. al. ‘17 - Masquerade MASQUERADE

  23. Medium-scale & True to the Person ! Hi-frequency detail !

  24. Medium-scale & True to the Person ! Hi-frequency detail !

  25. Medium-scale & True to the Person ! Hi-frequency detail !

  26. Issues in Geometric Approach Collapsing Geometry Specific features (lip shapes)

  27. Synthetic Data-driven Corrections on CG Creatures Sculpted Corrections for CG Creatures No FACS-based BlendShape-Rig

  28. Data-driven Corrections on CG Creatures Source Pre-Correction Post-Correction Hendler et. al. ‘17 - Direct Drive

  29. More examples - Wrinkle Map Regression

  30. Comparison Takes 1-2 Weeks Takes Several Months Shape-space built from Shape-space physical data modeled iteratively

  31. Final Result Overview of Data-Driven Facial Animation Markered Large-Scale face input Final High-Resolution Geomteric Deformation using Output Mesh low-resolution capture Training Data!!

  32. Final Result

  33. Acknowledgements Thanks to ~ David Corral, David Mclean, Rickey Cloudsdale, Lucio Moser, Geoff Wedig, Mark Williams, Ron Griswold, Nafees Bin Zafar, Doug Roble, Jeremy Buttell, Derek Crosby, Ron Miller, Darren Hendler and the entire Digital Domain Team! ~

Recommend


More recommend