1 / 52

SIGGRAPH Asia 2011 Preview Seminar Session 11: Animation

SIGGRAPH Asia 2011 Preview Seminar Session 11: Animation. 2011/11/25 Jun Saito Marza Animation Planet, Inc. Session 11: Animation. Artist Friendly Facial Animation Retargeting. Yeongho Seol ∗ , Jaewoo Seo † , Paul Hyunjin Kim ‡ , J.P. Lewis § , Junyong Noh ¶

infinity
Download Presentation

SIGGRAPH Asia 2011 Preview Seminar Session 11: Animation

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. SIGGRAPH Asia 2011Preview SeminarSession 11: Animation 2011/11/25 Jun Saito Marza Animation Planet, Inc.

  2. Session 11: Animation

  3. Artist Friendly Facial Animation Retargeting YeonghoSeol∗, JaewooSeo†, Paul HyunjinKim‡, J.P. Lewis§, JunyongNoh¶ ∗†‡¶KAIST, §Weta Digital

  4. Motivation Retargeting from facial motion capture does not yieldenough efficiency Artist Friendly Facial Animation Retargeting

  5. Side Note:Facial Retargeting Efficiency Technology X used at Marza

  6. System Overview Artist Friendly Facial Animation Retargeting

  7. Automatic GUI Generation • Facial rig w/ arrow-like GUI • Compute dominating motion vector of each blendshape target by WPCA • Grouping of GUI to regions and layers • Manually paint four regions: mouth, forehead, eyes, and others • Three layers (large, mid, small) depending on the total displacement from neutral face Artist Friendly Facial Animation Retargeting

  8. Retargeting Compute marker correspondence (generic face to actor’s face)by RBF warping Artist Friendly Facial Animation Retargeting

  9. Retargeting Conventional (non-sequential) retargeting Capturedmarker positions Marker positionsof blendshapes Artist Friendly Facial Animation Retargeting

  10. Retargeting Sequential retargeting • Solve NNLS for blendshape target starting with largest total displacement • Mimics animators’ workflow (coarse posing, then fine tuning) Artist Friendly Facial Animation Retargeting

  11. Graph Simplification • Find optimal salient points using dynamic programming • Find piecewise optimal Bezier curve Artist Friendly Facial Animation Retargeting

  12. Results Artist Friendly Facial Animation Retargeting

  13. Compression and Direct Manipulation of Complex Blendshape Models JaewooSeo∗, Geoffrey Irving†, J.P. Lewis‡, Junyong Noh§ ∗§KAIST, †‡Weta Digital

  14. Facial Blendshapes @ Weta: • 42,000 vertices • 730 targets • Density close to 100% • 8 fps on 8 core CPU Compression and Direct Manipulation of Complex Blendshape Models

  15. Side Note:Blendshapes @ Marza Generic model for feature-quality, semi-realistic character • 6,821 vertices • 96 targets • Average density: 10% (max 30%) Perhaps sparse matrix implementation is enough?

  16. Contributions Make humongous blendshapes more tractablewith lossy matrix compression usinghierarchical semi-separable (HSS) representation Technique can be applied to compression and speed-up of large matrix multiplication Compression and Direct Manipulation of Complex Blendshape Models

  17. Compression Preparation: reordering • Place high-rank blocks on “diagonal,” low-rank blocks on “off-diagonal” • Exact permutation is NP hard • Find bisection by minimizing crossing weight below, use heuristic in [Kernighan and Lin 1970] Compression and Direct Manipulation of Complex Blendshape Models

  18. Compression Hierarchical Semi-Separable (HSS) Representation Tree of orthogonal matrices to compresssignificant off-diagonal structure Compression and Direct Manipulation of Complex Blendshape Models

  19. Compression HSS Construction [Xia et al. 2010] Compression and Direct Manipulation of Complex Blendshape Models

  20. Compression HSS Construction [Xia et al. 2010] Compression and Direct Manipulation of Complex Blendshape Models

  21. Compression HSS Construction [Xia et al. 2010] Compression and Direct Manipulation of Complex Blendshape Models

  22. Compression HSS Construction [Xia et al. 2010] Compression and Direct Manipulation of Complex Blendshape Models

  23. Compression HSS Construction [Xia et al. 2010] Compression and Direct Manipulation of Complex Blendshape Models

  24. Compression • Perform SVD on matrix blocks, drop singular values • Optional: represent rotation using banded Householder factorization [Irving 2011] Compression and Direct Manipulation of Complex Blendshape Models

  25. Parallel Processing GPU-optimized HSS-compressed matrix multiplication Compression and Direct Manipulation of Complex Blendshape Models

  26. More Applications • Direct manipulation [Lewis and Anjyo 2010] with local influence • Cage deformation Compression and Direct Manipulation of Complex Blendshape Models

  27. Results Memory Speed (in milliseconds) Compression and Direct Manipulation of Complex Blendshape Models

  28. Controlling Physics-Based Characters Using Soft Contacts SumitJain and C. Karen Liu Georgia Institute of Technology

  29. Motivation VIDEO Controlling Physics-Based Characters Using Soft Contacts

  30. Contributions • Coupling of articulated rigid bodyand soft body with practical contact model • Experiments to show soft contact model stabilizes physically simulated characters Controlling Physics-Based Characters Using Soft Contacts

  31. Coupled Dynamics • Articulated rigid body Massmatrix Coriolismatrix Gravity Generalizedforces Jacobianat contact Contactforce Controlling Physics-Based Characters Using Soft Contacts

  32. Coupled Dynamics • Deformable body • Vertex deformation – tries to keep vertices at their rest positions • Edge deformation – tries to keep the relative positions of the vertices Stiffnessmatrix Dampingmatrix Controlling Physics-Based Characters Using Soft Contacts

  33. Coupled Dynamics • Rigid + Deformable • Adaptive deformable model • P-ring neighborhood of contact points aresimulated, rest are treated as rigid • Mass matrix is pre-computed at the rest positions Controlling Physics-Based Characters Using Soft Contacts

  34. Coupled Dynamics • Discretize with time step h Controlling Physics-Based Characters Using Soft Contacts

  35. Contact Model • Contact with friction as Linear Complementarity Problem (LCP) [Anitescu and Potra 1997] • Advantages over penalty-based methods: • Enforces work-less normal force, no penetration, and realistic slipping • Explicit deformation at contact increases contact points • Low stiffness in penalty methods causes frequent penetration Controlling Physics-Based Characters Using Soft Contacts

  36. Locomotion Control:SIMBICON • Compute joint torque τs • Detect collisions • Create contacts to be solved for in ODE • Apply τsto character in ODE • Advance one time step in ODE to get next state Controlling Physics-Based Characters Using Soft Contacts

  37. Locomotion Control:SIMBICON + Proposed Method • Compute joint torque τs • Detect collisions • Create contacts to be solved for in ODE • Convert τs to generalized torques τr • Convert state to generalized coordinates • Solve (qk+1, qk+1) and fc using LCP • Apply fc to character in ODE • Apply τsto character in ODE • Advance one time step in ODE to get next state Controlling Physics-Based Characters Using Soft Contacts

  38. Modal-Space Control for Articulated Characters SumitJain and C. Karen Liu Georgia Institute of Technology

  39. Motivation Arbitrary character simulation with both • long-term (anticipatory) planning • short-term (reactive) planning is prohibitively expensive to compute ? Externalforce Modal-Space Control for Articulated Characters

  40. Contribution Formulation of modal-space character control capable of long-term planning and frequent re-planning for simulating“specific motion sequence” Modal analysis provides: • Independent control: N-dimensional optimization to N independent one dimensional problems • Model reduction: Allows construction of a small number of strategies specific to certain frequencies of the dynamic system Modal-Space Control for Articulated Characters

  41. Modal Analysis Md and Kd are diagonal, thus N independent 1d problems Modal-Space Control for Articulated Characters

  42. Strategy For Modes • Rigid modes (zero frequency) • Corresponds to six eigenvectors in Φ with zero eigenvalues • Only affected by external forces • For long term planning • Low frequency modes • Corresponds to eigenvectors witheigenvalues smaller than some threshold • Visibly significant movementsby actuated system(see right) • For long term planning • High frequency modes • Less visually significant • For reactive planning 1st three principal componentsdominated by low frequency Modal-Space Control for Articulated Characters

  43. Control Summary • Rigid body modes: estimate contact forces • Solve QP, constrained by Coulomb friction, for ideal contact forces f*to match rigid mode reference state • Low frequency modes: estimate joint actuation • Solve unconstrained QP for ideal actuation Ia* to match low frequency reference state Modal-Space Control for Articulated Characters

  44. Control Summary • High frequency modes: track short-horizon plan • Analytically compute high-frequency actuation to match reference state • Corrective forces • Δf and ΔIa are computed to satisfy Coulomb friction Modal-Space Control for Articulated Characters

  45. Results VIDEO Modal-Space Control for Articulated Characters

  46. Stretchable and Twistable Bones for Skeletal Shape Deformation Alec Jacobson∗andOlga Sorkine† ∗New York University, †ETH Zurich

  47. Motivation • Conventional bone skinning methods cause unnatural deformation at the end of bones when scaled Stretchable and Twistable Bones for Skeletal Shape Deformation

  48. Linear Blend Skinning (LBS) • Weight for each bone Rotation Resultingposition Weight foreach bone Originalposition Scale Stretchable and Twistable Bones for Skeletal Shape Deformation

  49. Stretchable, Twistable Bones Skinning (STBS) • Weight for each bone and endpoint • Naturally extends to use dual quaternion Twist alongbone Weight foreach endpoint Stretchable and Twistable Bones for Skeletal Shape Deformation

  50. Results Stretchable and Twistable Bones for Skeletal Shape Deformation

More Related