1
|
- Michael Gleicher
- Department of Computer Sciences
- Nicola Ferrier
- Department of Mechanical Engineering
- University of Wisconsin-Madison
- http://www.cs.wisc.edu/graphics
|
2
|
- Motion capture for animation is hard!
- It’s hard in ways that are challenging for computer vision
- Despite advances in computer vision, don’t expect miracles too soon
|
3
|
- What do we want from motion capture?
- Why is this so hard?
- An experiment
- What do observations tell you
- Computer vision in this light
|
4
|
|
5
|
|
6
|
|
7
|
- Animation doesn’t really need high-precision and accuracy
- Not concerned about details
- Not doing measurement
- “Just” need to capture mood, emotion, intent, subtlety, personality, …
- All those things an actor can do
|
8
|
- Where does X live in the data?
- Where X Î {style,
personality, emotion, …}
- Small artifacts can destroy realism
- Eye is sensitive to certain details
- Amazing what you can’t get away with
- See Kovar, Schreiner and Gleicher, SCA ‘02
|
9
|
- Don’t know which details are important!
- Must preserve ALL details
- Since you don’t know what is important
- Need to understand artifiacts better
|
10
|
- Computer Puppetry
- Shin, Lee, Gleicher, Shin, Tog ’01.
|
11
|
- Capture “essense” only
- Add details later
- This is equivalent to the vision problem that we’re getting to.
- This motivated our work.
|
12
|
- Cheap capture devices
- Non-intrusive Ubiquitous
- Easy to obtain Inexpensive
- Easy to set up
- Single camera, video motion capture!
- Multiple cameras, might as well be mocap hardware
- How much can you get?
|
13
|
- Pinhole camera model
- Rigid skeleton
- Solve constrained-optimization for locations
|
14
|
- See paper for details
- Surprisingly low precision
- Surprisingly many ambiguities
- Weak model
- Few assumptions about motion
- Distance constraints
- Assume perfect observations
|
15
|
- Limited information -> Limited results
- Not much info in a 2D observation
- 2D observations are a constraint
- Limit the possible causes
- But still leave a large space
- How to choose amongst possibilities?
- Optimization?
- Probabilities?
|
16
|
- Computer vision human tracking works by using a stronger model
- Use more information about what motions are likely to choose amongst
possible interpretations
- Encode what motions are likely
- The hot topic in human tracking
- Rehg, Black, Forstythe, Reid, Brand, Shin, …
- Impressive success, varying methods for implentation of “likelihood”
|
17
|
- Encode “likely” or “common” motions
- Observations select from these
- Extreme: Matt Brand’s work
- Novice dances, plays motion of expert
- Doesn’t work for animation!
- Want ununusual, unlikely, specific, …
- If you had seen the motion before, why not just play it from database?
|
18
|
- Idea
- use more knowledge of human to limit possibilities
- Problems
- Need manipulatable representations for practicality
- Humans are complex
- Strong models only good if they are correct
- Unclear how much more constraint this adds
- Little exploration in vision
|
19
|
|
20
|
|
21
|
|
22
|
- Human tracking is improving
- Primarily through use of strong models
- New approaches may not work for animation
- Different quality goals
- Different applications (classification)
- Looks like we’ll have old approaches for a while
- “engineer” away vision problem
- Use expensive sensors
|
23
|
- UW Graphics group
- Our friends in the mocap industry
- National Science Foundation
- Mike: CCR-9984506, IIS-0097456
- Nicola: IRI-??
- Industrial and University sponsors
- Microsoft, Intel, Autodesk, Alias/Wavefront, Wisconsin Alumni Research
Foundation, IBM, Pixar
|