1. Pose Space Deformation:
A unified approach to shape interpolation and skeleton-driven deformation
J.P.Lewis, Matt Cordner, Nickson Fong
Centropolis

2. Character animation Body: Face animation:
“skeleton subspace deformation”
Face animation:
Shape interpolation (Tony de Peltrie, Star Wars, Dinosaur)
Custom procedural models (Parke, Toy Story)
Common practice for years

3. Pose Space Deformation
Combine direct geometric shape interpolation and skeleton driven deformation
address the limitations of Shape Interpolation and Skeleton-driven deformation

4. Shape interpolation “Blend shapes, multi-target morphs, ”
Weighted sum of key shapes
Or delta shapes...

5. Shape interpolation (delta)
delta shapes: equivalent!
(combinations)

6. Shape Interpolation Advantages Disadvantages direct manipulation
desired targets are achieved
Disadvantages
Superposition, not independent, linear subspace

7. Skeleton Subspace Deformation (SSD)
“enveloping”, ...
Symbolics, Softimage
Weighted sum of surface point as transformed by various coordinate frames.
Diagram

8. SSD problems: collapse

9. SSD problems Collapses, No direct manipulation,
You can’t tell when you’re done

10. Goal
Combine direct geometric shape interpolation and skeleton driven deformation
BODY: use shape interpolation to control shoulder shape as it deforms according to the skeleton
FACE: drive the face using jaw rotation rather than linear interpolation
address the limitations of SI, SSD

11. Related work Combine skeletal and local deformation control
Burtnyk and Wein, 1976

12. Related work: Idea #1 Animation as scattered interpolation
Van Overveld, 1990;
Litwinowicz & Williams 1994
Apply wide literature of interpolation directly to our animation problem!

13. Related work: Idea #2 Animation, etc. as general functional mapping
Poggio & Brunelli 1992;
Lewis 1988, 91

14. Synthesis
attempt #1
Lewis 95: shape interpolation in the context of SSD

15. Related work
Symbolics/Nichimen 91
Maya
Interpolation
Addition

16. Pose space deformation
Surface cv
movement
Neck Joint
R. Upper Arm
Left Upper Arm
Pose Space:
N Dimensions
Surface CV movement:
3 dimensions

17. Skeleton driven PSD elbow, f( rotation, load )
face is f( jaw rotation, emotion, phoneme...)
quadruped leg/chest/neck

18. Scattered Interpolation
Shepard
Wiener interpolation, Kriging
Others...
Radial Basis functions
universal approximation
smooth if smooth kernel
large literature
Voronoi/delauney

19. VIDEO: Skeleton driven PSD

20. PSD vs. Shape Interpolation (SI)
use same set of sculpted key shapes/delta shapes
Shape Interpolation is superposition; PSD interpolates
SI A B C crossfade is piecewise linear; PSD is smooth if desired

21. Shape Interpolation vs. PSD
adds
one dimension per shape
not orthogonal
animator manually solves for the representation
interpolates
shapes placed as desired in desired space

22. Shape Interpolation: reinforcement / fighting
Adding smirk counteracts raise
Dinosaur: 100+ face shapes + =
raise
smirk

23. PSD facial animation Delighted ? Serene Pleased <linear>
Distressed
<neutral>

24. VIDEO: PSD facial animation
Aroused
J.A.Russell, 1980
(simplified)
alarmed
delighted
frustrated
Displeasure
Pleasure
serene
tired
Sleepy

25. Conclusion
Unification / simplification / modest improvement to existing common practice
How many poses? Like shape interpolation, more is better, up to a point...
Future: Learn the space?
Example code: (september)

28. SSD Schematic
Robot arm, two cylinders bent at the elbow

29. SSD Schematic

30. Related work
Combine skeletal and local deformation control (Burtnyk and Wein, 1976)
Animation as scattered interpolation (Van Overveld, 1990; Litwinowicz & Williams 1994)
Animation as general functional mapping (Poggio & Brunelli 1992; Lewis 1988, 91)
Lewis 95

31. PSD algorithm steps Definitions: pose, pose space Sculpt
Define delta(pose)
Solve
Synthesize, evaluate, adjust, repeat

32. PSD vs. Shape Interpolation
SI: adds, not orthogonal,
one dimension per shape
PSD: interpolates; shapes
placed as desired in space

33. PSD/SI facial animation
SI shapes define independent axes, PSD shapes are positioned as desired in desired space
PSD: animator plans interpolation path. SI: animator also has to solve for this path in a non-orthogonal basis
PSD is smooth (if desired)

34. Related Documents Marketing plan Budget Post mortem Submit questions
Location or contact name/phone
Budget
Post mortem
Submit questions

35. Project Goals Ultimate goal of project Relationship to other projects
High-level timing goals

36. Description Describe the project in non-technical terms.
Use following slides for discussing status, schedules, budget, etc.
FOR MORE INFO...
List location or contact for specification (or other related documents) here

37. Competitive Analysis Competitors Strengths Weaknesses
(You may want to allocate one slide per competitor)
Strengths
Your strengths relative to competitors
Weaknesses
Your weaknesses relative to competitor

38. Competitive Analysis, Cont.
Competitors
Strengths
Weaknesses
FOR MORE INFO...
List location or contact for competitive analysis (or other related documents) here

39. Technology New technology being used Standards being adopted
Benefits
Standards being adopted
Standards specifically being ignored
Drawbacks & benefits
DYA: define your acronyms!