Animating (human) motion Presented by: –Yoram Atir –Simon Adar.
-
Upload
daniella-phillips -
Category
Documents
-
view
225 -
download
1
Transcript of Animating (human) motion Presented by: –Yoram Atir –Simon Adar.
![Page 1: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/1.jpg)
C.Bregler, L.Loeb, E.Chuang, H.Deshpande; "Turning to the Masters: Motion Capturing Cartoons”
Animating (human) motion
• Presented by:– Yoram Atir– Simon Adar
![Page 2: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/2.jpg)
C.Bregler, L.Loeb, E.Chuang, H.Deshpande; "Turning to the Masters: Motion Capturing Cartoons”
Applications of computer animation
• Movies
• Advertising
• Games
• Simulators
• …
![Page 3: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/3.jpg)
C.Bregler, L.Loeb, E.Chuang, H.Deshpande; "Turning to the Masters: Motion Capturing Cartoons”
General goals of the work presented
- New methods aimed to save time/money/skills needed.
- Study motion (texture).
![Page 4: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/4.jpg)
C.Bregler, L.Loeb, E.Chuang, H.Deshpande; "Turning to the Masters: Motion Capturing Cartoons”
Agenda
- Basic concepts
- Motion Synthesis/texture using motion capture- Physics/Biomechanics Motion Synthesis
- Cartoon Motion Retargeting.
![Page 5: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/5.jpg)
Basic Concepts
Basic concepts
• Animation world (3D)
• Skeletal model representation
• Model positioning
• Keyframes
• Motion capture
• Frequency bands
• Correlations
![Page 6: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/6.jpg)
Basic Concepts
3D animation world
- (Human) model is animated in Object space- Animated model projected into “global” space- Camera is placed and rotated- Perspective is set- Other…
![Page 7: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/7.jpg)
Basic Concepts
Skeletal representation
- Each model has its own Default Pose
- DOF’s – joint angles/translations relative to Default Pose
- Hierarchical (tree) skeletal representation of model
Picture from Lecture in Computer Graphics course
Department of computer science
University of Washington
![Page 8: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/8.jpg)
Basic Concepts
Creating motion
- Skeletal variations between frames- Overall rotation/Translation between frames- Correlate.
General Problem:
A LOT of work due to the large number of DOFS & high frame rate
![Page 9: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/9.jpg)
Basic Concepts
Figure positioning
- Forward kinematics (simplified): Figure positioning by joint data specification.
Problem:- Tedious trial and error.
![Page 10: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/10.jpg)
Basic Concepts
Figure positioning
Inverse kinematics (simplified)- Joint data is acquired by solving for the final position- In general, This is an optimization problem with a large system
of variables and constraints- Problems often are expressed as minimization problems, and
solved using standard algorithms (gradient decent etc).- Usually, infinite number of possible solutions.- A “good” solution has to be more than “feasible”- Often one is obtained by embedding specific knowledge as
additional constraints, and/or- Using Inverse kinematics as a part of a specific solution.
![Page 11: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/11.jpg)
Basic Concepts
Basic methods for saving labor
Motion captureKeyFrames
![Page 12: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/12.jpg)
Basic Concepts
Keyframes
– Specifying only part of DOFs and frames– Computer interpolation between them
Problem: “smooth” interpolation looks unreal
There are methods to apply “specific noise”
– Term has historical roots
![Page 13: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/13.jpg)
Basic Concepts
Motion capture
– Acquired from “live action”– Copied onto animated character
• Problem: Hard to adapt.• “Motion Editing” – methods to adapt mocap
– Done in studios– Mocap libraries exist
![Page 14: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/14.jpg)
Basic Concepts
Keyframing vs. MocapKeyframing vs. Mocap
Keyframing
Mocap
DisadvantagesAdvantages
•Control
![Page 15: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/15.jpg)
Basic Concepts
Keyframing vs. MocapKeyframing vs. Mocap
Keyframing
Mocap
DisadvantagesAdvantages
•Control•Intuitive
![Page 16: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/16.jpg)
Basic Concepts
Keyframing vs. MocapKeyframing vs. Mocap
Keyframing
Mocap
DisadvantagesAdvantages
•Control•Intuitive
•Detail hard
![Page 17: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/17.jpg)
Basic Concepts
Keyframing vs. MocapKeyframing vs. Mocap
Keyframing
Mocap
DisadvantagesAdvantages
•Control•Intuitive
•Detail hard•Many DOF
![Page 18: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/18.jpg)
Basic Concepts
Keyframing vs. MocapKeyframing vs. Mocap
Keyframing
Mocap
DisadvantagesAdvantages
•Control•Intuitive
•Detail hard•Many DOF
•Detail easy
![Page 19: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/19.jpg)
Basic Concepts
Keyframing vs. MocapKeyframing vs. Mocap
Keyframing
Mocap
DisadvantagesAdvantages
•Control•Intuitive
•Detail hard•Many DOF
•Detail easy•All DOF
![Page 20: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/20.jpg)
Basic Concepts
Keyframing vs. MocapKeyframing vs. Mocap
Keyframing
Mocap
DisadvantagesAdvantages
•Control•Intuitive
•No control
•Detail hard•Many DOF
•Detail easy•All DOF
![Page 21: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/21.jpg)
Basic Concepts
Keyframing vs. MocapKeyframing vs. Mocap
Keyframing
Mocap
DisadvantagesAdvantages
•Control•Intuitive
•No control•Not intuitive
•Detail hard•Many DOF
•Detail easy•All DOF
![Page 22: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/22.jpg)
Keyframe Data vs. Motion Capture DataKeyframe Data vs.
Motion Capture Data
![Page 23: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/23.jpg)
Basic Concepts
Frequency Bands
Right flat Right toe Left flat Left toe
![Page 24: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/24.jpg)
Basic Concepts
Frequency Bands
• Simplifies the form of the data– Low frequency Variations:
Large scale motions.– Higher frequency variations:
individual “noise” / Jitter
Both are important to preserve in order to capture the essence of motion
![Page 25: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/25.jpg)
Basic Concepts
Correlations
• Joints angle/translation data is related to each other
• Joint angles are correlated over time
• Correlation “plot” is– (somewhat) Specific to the type
of motion– Carries “personality” information
(style)
![Page 26: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/26.jpg)
C.Bregler, L.Loeb, E.Chuang, H.Deshpande; "Turning to the Masters: Motion Capturing Cartoons”
More information…
INTRODUCTION TO COMPUTER ANIMATION – Rick parent
http://www.cis.ohio-state.edu/~parent/book/outline.html
Splines
http://www.people.nnov.ru/fractal/splines/Intro.html
Hash Inc - Animation software (Movies, tutorials…)
http://www.hash.com
Google…
![Page 27: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/27.jpg)
C.Bregler, L.Loeb, E.Chuang, H.Deshpande; "Turning to the Masters: Motion Capturing Cartoons”
Agenda
- Basic concepts
- Motion Synthesis/texture using motion capture- Physics/Biomechanics Motion Synthesis
- Cartoon Motion Retargeting
![Page 28: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/28.jpg)
Goal: Motion Capture Assisted Animation
Goal: Motion Capture Assisted Animation
• Create a method that allows an artist low-level control of the motion
• Combine the strengths of keyframe animation with those of mocap
• Create a method that allows an artist low-level control of the motion
• Combine the strengths of keyframe animation with those of mocap
Motion Capture Assisted Animation – Pullen/Bregler
![Page 29: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/29.jpg)
Goal: Motion Capture Assisted Animation
Goal: Motion Capture Assisted Animation
“Sketch” an animation by keyframing• Animate only a few degrees of freedom
• Set few keyframes
“Enhance” the result with mocap data• Synthesize missing degrees of freedom
• Texture keyframed degrees of freedom
“Sketch” an animation by keyframing• Animate only a few degrees of freedom
• Set few keyframes
“Enhance” the result with mocap data• Synthesize missing degrees of freedom
• Texture keyframed degrees of freedom
Motion Capture Assisted Animation – Pullen/Bregler
![Page 30: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/30.jpg)
C.Bregler, L.Loeb, E.Chuang, H.Deshpande; "Turning to the Masters: Motion Capturing Cartoons”
What is a Motion Texture?
• Every individual’s movement is unique
• Synthetic motion should capture the texture
• To “texture” means to add style to a pre-existing motion
• Technically, texturing is a special case of synthesis
![Page 31: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/31.jpg)
Goal: Motion Capture Assisted Animation
Goal: Motion Capture Assisted Animation
Blue = Keyframed
Purple = Textured/Synthesized
Motion Capture Assisted Animation – Pullen/Bregler
![Page 32: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/32.jpg)
How an Animator WorksHow an Animator Works
• A few degrees of freedom at first
• Not in detail
• Fill in detail with more keyframes later
• A few degrees of freedom at first
• Not in detail
• Fill in detail with more keyframes later
Motion Capture Assisted Animation – Pullen/Bregler
![Page 33: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/33.jpg)
The Method in WordsThe Method in Words
• Choose degrees of freedom to drive the animation
• Compare these degrees of freedom from the keyframed data to mocap
• Find similar regions
• Look at what the rest of the body is doing in those regions
• Put that data onto the keyframed animation
• Choose degrees of freedom to drive the animation
• Compare these degrees of freedom from the keyframed data to mocap
• Find similar regions
• Look at what the rest of the body is doing in those regions
• Put that data onto the keyframed animation
Motion Capture Assisted Animation – Pullen/Bregler
![Page 34: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/34.jpg)
Choices the Animator Must Make
1. Which DOF to use as matching angles
2. Which DOF to texture, which to synthesize
3. Which frequency band to use in matching
4. How many frequency bands to use in texturing
5. How many matches to keep
6. How many best paths to keep
1. Which DOF to use as matching angles
2. Which DOF to texture, which to synthesize
3. Which frequency band to use in matching
4. How many frequency bands to use in texturing
5. How many matches to keep
6. How many best paths to keepMotion Capture Assisted Animation – Pullen/Bregler
![Page 35: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/35.jpg)
Before Beginning:Choose Matching Angles
Before Beginning:Choose Matching Angles
Left Hip xLeft Hip yLeft Hip zLeft Knee xLeft Knee yLeft Knee zLeft Ankle xLeft Ankle yLeft Ankle zLeft Ball xLeft Ball yLeft Ball zRight Hip xRight Hip yRight Hip zRight Knee xRight Knee yRight Knee zRight Ankle xRight Ankle yRight Ankle zRight Ball xRight Ball yRight Ball z
Root x transRoot y transRoot z transRoot x rotRoot y rotRoot z rotSpine1 xSpine1 ySpine1 zSpine2 xSpine2 ySpine2 zSpine3 xSpine3 ySpine3 zNeck xNeck yNeck zHead xHead yHead zHead Aim xHead Aim yHead Aim z
Left Clavicle xLeft Clavicle yLeft Clavicle zLeft Shoulder xLeft Shoulder yLeft Shoulder zLeft Elbow xLeft Elbow yLeft Elbow zLeft Wrist xLeft Wrist yLeft Wrist zRight Clavicle xRight Clavicle yRight Clavicle zRight Shoulder xRight Shoulder yRight Shoulder zRight Elbow xRight Elbow yRight Elbow zRight Wrist xRight Wrist yRight Wrist z
Time TimeTime
![Page 36: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/36.jpg)
Matching Angles Drive the SynthesisMatching Angles
Drive the Synthesis
Left Hip xLeft Hip yLeft Hip zLeft Knee xLeft Knee yLeft Knee zLeft Ankle xLeft Ankle yLeft Ankle zLeft Ball xLeft Ball yLeft Ball zRight Hip xRight Hip yRight Hip zRight Knee xRight Knee yRight Knee zRight Ankle xRight Ankle yRight Ankle zRight Ball xRight Ball yRight Ball z
Root x transRoot y transRoot z transRoot x rotRoot y rotRoot z rotSpine1 xSpine1 ySpine1 zSpine2 xSpine2 ySpine2 zSpine3 xSpine3 ySpine3 zNeck xNeck yNeck zHead xHead yHead zHead Aim xHead Aim yHead Aim z
Left Clavicle xLeft Clavicle yLeft Clavicle zLeft Shoulder xLeft Shoulder yLeft Shoulder zLeft Elbow xLeft Elbow yLeft Elbow zLeft Wrist xLeft Wrist yLeft Wrist zRight Clavicle xRight Clavicle yRight Clavicle zRight Shoulder xRight Shoulder yRight Shoulder zRight Elbow xRight Elbow yRight Elbow zRight Wrist xRight Wrist yRight Wrist z
Time TimeTime
![Page 37: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/37.jpg)
Motion Capture DataMotion Capture Data
Left Hip xLeft Hip yLeft Hip zLeft Knee xLeft Knee yLeft Knee zLeft Ankle xLeft Ankle yLeft Ankle zLeft Ball xLeft Ball yLeft Ball zRight Hip xRight Hip yRight Hip zRight Knee xRight Knee yRight Knee zRight Ankle xRight Ankle yRight Ankle zRight Ball xRight Ball yRight Ball z
Root x transRoot y transRoot z transRoot x rotRoot y rotRoot z rotSpine1 xSpine1 ySpine1 zSpine2 xSpine2 ySpine2 zSpine3 xSpine3 ySpine3 zNeck xNeck yNeck zHead xHead yHead zHead Aim xHead Aim yHead Aim z
Left Clavicle xLeft Clavicle yLeft Clavicle zLeft Shoulder xLeft Shoulder yLeft Shoulder zLeft Elbow xLeft Elbow yLeft Elbow zLeft Wrist xLeft Wrist yLeft Wrist zRight Clavicle xRight Clavicle yRight Clavicle zRight Shoulder xRight Shoulder yRight Shoulder zRight Elbow xRight Elbow yRight Elbow zRight Wrist xRight Wrist yRight Wrist z
Time TimeTime
![Page 38: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/38.jpg)
OverviewOverview
Steps in texture/synthesis method
• Frequency analysis
• Matching
• Path finding
• Joining
Steps in texture/synthesis method
• Frequency analysis
• Matching
• Path finding
• Joining
Motion Capture Assisted Animation – Pullen/Bregler
![Page 39: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/39.jpg)
In the following series of slides:
Hip angle = matching angle
Spine angle = angle being synthesized
In the following series of slides:
Hip angle = matching angle
Spine angle = angle being synthesized
Example
Motion Capture Assisted Animation – Pullen/Bregler
![Page 40: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/40.jpg)
Frequency Analysis:Break into Bands
Motion Capture Assisted Animation – Pullen/Bregler
![Page 41: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/41.jpg)
Fre
quen
cy
Time
Band-pass decomposition of matching angles
Keyframed Data Motion Capture Data
Frequency Analysis
Motion Capture Assisted Animation – Pullen/Bregler
![Page 42: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/42.jpg)
Fre
quen
cy
Time
Keyframed Data Motion Capture Data
Chosen low frequency band
Frequency Analysis
Motion Capture Assisted Animation – Pullen/Bregler
![Page 43: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/43.jpg)
Keyframed Data Motion Capture Data
Hip angle data (a matching angle)
Chosen Low Frequency Band
Motion Capture Assisted Animation – Pullen/Bregler
![Page 44: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/44.jpg)
Keyframed Data Motion Capture Data
Making Fragments
Break where first derivative changes sign
Motion Capture Assisted Animation – Pullen/Bregler
![Page 45: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/45.jpg)
Keyframed Data Motion Capture Data
Making Fragments
Step through fragments one by one
Motion Capture Assisted Animation – Pullen/Bregler
![Page 46: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/46.jpg)
Matching
KeyframedFragment
Motion Capture Assisted Animation – Pullen/Bregler
![Page 47: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/47.jpg)
Matching
KeyframedFragment
Motion Capture Data
Motion Capture Assisted Animation – Pullen/Bregler
![Page 48: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/48.jpg)
Matching
KeyframedFragment
Motion Capture Data
Motion Capture Assisted Animation – Pullen/Bregler
![Page 49: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/49.jpg)
Matching
Compare to all motion capture fragmentsA
ngle
in d
egre
es
Time
KeyframedMocap
![Page 50: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/50.jpg)
Matching
Resample mocap fragments to be same lengthA
ngle
in d
egre
es
Time
KeyframedMocap
![Page 51: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/51.jpg)
MatchingUsing some metric on all matching anglesand on their first derivatives:
Keep the K closest matches
Ang
le in
deg
rees
Time
KeyframedMocap
![Page 52: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/52.jpg)
Matching
KeyframedFragment
Motion Capture Data
Motion Capture Assisted Animation – Pullen/Bregler
![Page 53: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/53.jpg)
Matching
KeyframedFragment
Motion Capture Data
CloseMatches
Motion Capture Assisted Animation – Pullen/Bregler
![Page 54: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/54.jpg)
Matching
Hip Angle (Matching Angle)
Spine Angle (For Synthesis)
Motion Capture Assisted Animation – Pullen/Bregler
![Page 55: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/55.jpg)
Matching and Synthesis
Low frequency hip angle data (a matching angle)
Spine angle data to be synthesized
Motion Capture Assisted Animation – Pullen/Bregler
![Page 56: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/56.jpg)
Matching and Synthesis
Low frequency hip angle data (a matching angle)
Spine angle data to be synthesized
Motion Capture Assisted Animation – Pullen/Bregler
![Page 57: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/57.jpg)
Matching and Synthesis
Low frequency hip angle data (a matching angle)
Spine angle data to be synthesized
Motion Capture Assisted Animation – Pullen/Bregler
![Page 58: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/58.jpg)
Matching and Synthesis
Low frequency hip angle data (a matching angle)
Spine angle data to be synthesized
Motion Capture Assisted Animation – Pullen/Bregler
![Page 59: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/59.jpg)
Matching and Synthesis
Low frequency hip angle data (a matching angle)
Spine angle data to be synthesized
Motion Capture Assisted Animation – Pullen/Bregler
![Page 60: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/60.jpg)
Matching and Synthesis
Low frequency hip angle data (a matching angle)
Spine angle data to be synthesized
Motion Capture Assisted Animation – Pullen/Bregler
![Page 61: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/61.jpg)
Possible Synthetic Spine Angle Data
Ang
le in
deg
rees
Time
![Page 62: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/62.jpg)
Path FindingA
ngle
in d
egre
es
Time
We would like to:
• Use as much consecutive fragments as possible
• Stay as close as possible to best fit
![Page 63: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/63.jpg)
Path FindingA
ngle
in d
egre
es
Time
![Page 64: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/64.jpg)
Path FindingA
ngle
in d
egre
es
Time
![Page 65: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/65.jpg)
Path FindingA
ngle
in d
egre
es
Time
![Page 66: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/66.jpg)
Path FindingA
ngle
in d
egre
es
Time
![Page 67: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/67.jpg)
JoiningA
ngle
in d
egre
es
Time
![Page 68: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/68.jpg)
Enhancing Animations:Texturing and SynthesisEnhancing Animations:Texturing and Synthesis
Keyframed
Textured Synthesized
Not keyframed
![Page 69: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/69.jpg)
Texturing
Synthesize upper frequency bands
Motion Capture Assisted Animation – Pullen/Bregler
![Page 70: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/70.jpg)
Texturing
Band-pass decomposition of keyframed dataF
requ
ency
Time
![Page 71: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/71.jpg)
Texturing
Synthesize upper frequency bandsF
requ
ency
Time
![Page 72: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/72.jpg)
Walking animationsTexturing and Synthesis
Keyframed Sketch
![Page 73: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/73.jpg)
Walking animationsTexturing and Synthesis
Motion Capture Data
Two different styles of walk
![Page 74: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/74.jpg)
Walking animationsTexturing and Synthesis
Enhanced Animation
Upper body is synthesized
Lower body is textured
![Page 75: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/75.jpg)
Otter Animations: TexturingKeyframed data
![Page 76: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/76.jpg)
Otter Animations: TexturingTextured animation
![Page 77: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/77.jpg)
Dance Animations: Texturing and Synthesis
Lazy Keyframed Sketch
![Page 78: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/78.jpg)
Dance Animations: Texturing and Synthesis
Motion Capture Data
![Page 79: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/79.jpg)
Dance Animations: Texturing and Synthesis
Enhanced AnimationBlue = Keyframed
Purple = Textured/Synthesized
![Page 80: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/80.jpg)
Dance Animations: Texturing
Keyframed Sketch With More Detail
![Page 81: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/81.jpg)
Dance Animations: TexturingTextured Animation
Blue = Keyframed
Purple = Textured
![Page 82: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/82.jpg)
Summary of the Method
Keyframed data
Mocap Data
Keyframed Data
Mocap Data Possible Synthetic Data
Matching Angles
Sketch + Mocap
Frequency Analysis Matching
Path Finding JoiningEnhanced Animation
![Page 83: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/83.jpg)
Choices the Animator Must Make
1. Which DOF to use as matching angles
2. Which DOF to texture, which to synthesize
3. Which frequency band to use in matching
4. How many frequency bands to use in texturing
5. How many matches to keep
6. How many best paths to keep
1. Which DOF to use as matching angles
2. Which DOF to texture, which to synthesize
3. Which frequency band to use in matching
4. How many frequency bands to use in texturing
5. How many matches to keep
6. How many best paths to keep
![Page 84: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/84.jpg)
Conclusions and Applications
• Appropriate for an artist interested in a very particular style of motion
• The artist may have a relatively small motion capture set of that style
• The artist may want precise control over parts of the motion
• Appropriate for an artist interested in a very particular style of motion
• The artist may have a relatively small motion capture set of that style
• The artist may want precise control over parts of the motion
![Page 85: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/85.jpg)
Conclusions and Further Work
• Direct incorporation of hard constraints
• Fundamental units of motion
• Direct incorporation of hard constraints
• Fundamental units of motion
![Page 86: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/86.jpg)
For more info . . .
http://graphics.stanford.edu/~pullen
Special Thanks to:Reardon Steele, Electronic Arts
![Page 87: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/87.jpg)
C.Bregler, L.Loeb, E.Chuang, H.Deshpande; "Turning to the Masters: Motion Capturing Cartoons”
Agenda
- Basic concepts
- Motion Synthesis/texture using motion capture- Physics, Biomechanics Motion Synthesis
- Cartoon Motion Retargeting
![Page 88: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/88.jpg)
C. Karen Liu & Zoran Popovi´c "Synthesis of Complex Dynamic Character Motion from Simple Animations"
Motivation
• Generate rapid prototyping of realistic character motion
• Avoid simulated human models, that are very complex, and don’t always look realistic
![Page 89: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/89.jpg)
C. Karen Liu & Zoran Popovi´c "Synthesis of Complex Dynamic Character Motion from Simple Animations"
Scope
• Highly dynamic movement such as jumping, kicking, running, and gymnastics.
• Less energetic motions such as walking or reaching will not work well in this framework
![Page 90: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/90.jpg)
C. Karen Liu & Zoran Popovi´c "Synthesis of Complex Dynamic Character Motion from Simple Animations"
Overview of the process
Motion sketch
Character description
Motion DB
User interaction
Constraint & phase detection
Transition pose synthesis
Objective functions Optimization Animation
Momentum control
![Page 91: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/91.jpg)
C. Karen Liu & Zoran Popovi´c "Synthesis of Complex Dynamic Character Motion from Simple Animations"
Overview of the process
• The objective is to transforms simple animations into realistic character motion by applying laws of physics and the biomechanics domain
• The unknowns are: values of joint angles and parameters of angular and linear momentum
![Page 92: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/92.jpg)
C. Karen Liu & Zoran Popovi´c "Synthesis of Complex Dynamic Character Motion from Simple Animations"
Overview of the process
Motion sketch
Character description
Motion DB
User interaction
Constraint & phase detection
Transition pose synthesis
Objective functions Optimization Animation
Momentum control
![Page 93: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/93.jpg)
C. Karen Liu & Zoran Popovi´c "Synthesis of Complex Dynamic Character Motion from Simple Animations"
Constraint and stage detection
• Each input sequence has two parts:– The part that needs to
be improved – The part that needs to
kept intacked
• Automatically extract the positional and sliding constrains
![Page 94: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/94.jpg)
C. Karen Liu & Zoran Popovi´c "Synthesis of Complex Dynamic Character Motion from Simple Animations"
Positional constraint detection
• A positional constraint fixes a specific point on the character to a stationary location for a period of time
• We need to find if all these points lie on a line, plane
• In an articulated character we find the constraints on each body part
![Page 95: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/95.jpg)
C. Karen Liu & Zoran Popovi´c "Synthesis of Complex Dynamic Character Motion from Simple Animations"
Positional constraint detection
• The algorithm looks for fixed points (point, line, plane)
iii xxT
0)( ii xIT
![Page 96: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/96.jpg)
C. Karen Liu & Zoran Popovi´c "Synthesis of Complex Dynamic Character Motion from Simple Animations"
Sliding constraints
i
iilp lpWTDist ),(min ,
![Page 97: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/97.jpg)
C. Karen Liu & Zoran Popovi´c "Synthesis of Complex Dynamic Character Motion from Simple Animations"
Overview of the process
Motion sketch
Character description
Motion DB
User interaction
Constraint & phase detection
Transition pose synthesis
Objective functions Optimization Animation
Momentum control
![Page 98: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/98.jpg)
C. Karen Liu & Zoran Popovi´c "Synthesis of Complex Dynamic Character Motion from Simple Animations"
Transition pose generation
• A transition pose separates constrained and unconstrained stages.
• Two possibilities:– We ask the animator
to draw the transition poses
– We have an estimator to suggest a transition pose
![Page 99: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/99.jpg)
C. Karen Liu & Zoran Popovi´c "Synthesis of Complex Dynamic Character Motion from Simple Animations"
Transition Pose Estimator• DB contains examples of different motions• The input of that DB are the motion
parameters like: flight distance, flight height, takeoff angle, landing angle, spin angle..
• The DB has a simplified representation of the transition poses by three COM’s
• We use IK to obtain the full character’s pose from those three COM’s
• The KNN - K nearest neighbor algorithm• The pose estimator predicts the candidate
pose by interpolating the KNN with the weights that describe the similarity to the input.
2
2AB )C(C
A
B
ABC
CCC
![Page 100: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/100.jpg)
C. Karen Liu & Zoran Popovi´c "Synthesis of Complex Dynamic Character Motion from Simple Animations"
Overview of the process
Motion sketch
Character description
Motion DB
User interaction
Constraint & phase detection
Transition pose synthesis
Objective functions Optimization Animation
Momentum control
![Page 101: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/101.jpg)
C. Karen Liu & Zoran Popovi´c "Synthesis of Complex Dynamic Character Motion from Simple Animations"
Momentum control
• Transition poses constrain the motion at few key points of the animation
• Dynamic constraints ensure realistic motion of each segment
• Linear and angular momentum give us these dynamic constraints
![Page 102: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/102.jpg)
C. Karen Liu & Zoran Popovi´c "Synthesis of Complex Dynamic Character Motion from Simple Animations"
Momentum during unconstrained and constrained stages
• linear momentum - During “flight” the only force is gravity
• Angular momentum - During “flight” there is no change in Angular momentum
• During “ground” stage we avoid computing the momentums and use empirical characteristics
mgdt
qdP
)(
0)(
dt
qdL
![Page 103: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/103.jpg)
C. Karen Liu & Zoran Popovi´c "Synthesis of Complex Dynamic Character Motion from Simple Animations"
Overview of the process
Motion sketch
Character description
Motion DB
User interaction
Constraint & phase detection
Transition pose synthesis
Objective functions Optimization Animation
Momentum control
![Page 104: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/104.jpg)
C. Karen Liu & Zoran Popovi´c "Synthesis of Complex Dynamic Character Motion from Simple Animations"
Objective functions
• There are three Objective functions, the basic idea behind them is power consumption– Minimum mass displacement– Minimal velocity of DOFs– Static balance
![Page 105: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/105.jpg)
C. Karen Liu & Zoran Popovi´c "Synthesis of Complex Dynamic Character Motion from Simple Animations"
Overview of the process
Motion sketch
Character description
Motion DB
User interaction
Constraint & phase detection
Transition pose synthesis
Objective functions Optimization Animation
Momentum control
![Page 106: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/106.jpg)
C. Karen Liu & Zoran Popovi´c "Synthesis of Complex Dynamic Character Motion from Simple Animations"
Putting it all together
• Environment constraints (Ce)• Transition pose constraints (Cp)• Momentum constraints (Cm)• Q are character’s DOFs
subject to )(min i
QqEi
0)(
0)(
0)(
QC
QC
QC
m
p
e
![Page 107: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/107.jpg)
C. Karen Liu & Zoran Popovi´c "Synthesis of Complex Dynamic Character Motion from Simple Animations"
Overview of the process
Motion sketch
Character description
Motion DB
User interaction
Constraint & phase detection
Transition pose synthesis
Objective functions Optimization Animation
Momentum control
![Page 108: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/108.jpg)
C. Karen Liu & Zoran Popovi´c "Synthesis of Complex Dynamic Character Motion from Simple Animations"
Some Results• Wide variety of figures: male, female, child• 51 DOFs • The body dimensions and mass distribution is taken from
biomechanics literature• In some of the cases the animator selects the body parts to be
constraints• The animator can change relative timing between each phase• The optimization was solved by using SNOPT a general
nonlinearly-constrained optimization package• The optimization time depends on the duration of the animation• All of the simple animation took less than five minutes to sketch • For all examples the synthesis process took less than five
minutes
![Page 109: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/109.jpg)
C. Karen Liu & Zoran Popovi´c "Synthesis of Complex Dynamic Character Motion from Simple Animations"
Broad jump
• Only 3 keyframes at takeoff, peak and landing
![Page 110: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/110.jpg)
C. Karen Liu & Zoran Popovi´c "Synthesis of Complex Dynamic Character Motion from Simple Animations"
Running
• The angular momentum constraint creates a counter-body movement by the shoulders and arms to counteract the angular momentum generated by the legs.
• Keyframing 7 DOFs
![Page 111: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/111.jpg)
C. Karen Liu & Zoran Popovi´c "Synthesis of Complex Dynamic Character Motion from Simple Animations"
Hopscotch
• Each hop requires 3 keyframes and has fewer than 7 DOFs
![Page 112: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/112.jpg)
C. Karen Liu & Zoran Popovi´c "Synthesis of Complex Dynamic Character Motion from Simple Animations"
Handspring
• There were no handstands within the DB so the user had to modify the result
![Page 113: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/113.jpg)
C. Karen Liu & Zoran Popovi´c "Synthesis of Complex Dynamic Character Motion from Simple Animations"
High-bar
• Two constraints stages: the bar and ground
![Page 114: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/114.jpg)
C. Karen Liu & Zoran Popovi´c "Synthesis of Complex Dynamic Character Motion from Simple Animations"
Karate kick
• A second synthesis add a keyframe in the peak
![Page 115: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/115.jpg)
C. Karen Liu & Zoran Popovi´c "Synthesis of Complex Dynamic Character Motion from Simple Animations"
Twist jumps
![Page 116: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/116.jpg)
C.Bregler, L.Loeb, E.Chuang, H.Deshpande; "Turning to the Masters: Motion Capturing Cartoons”
Agenda
- Basic concepts
- Motion Synthesis/texture using motion capture- Physics/Biomechanics Motion Synthesis
- Cartoon Motion Retargeting
![Page 117: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/117.jpg)
C.Bregler, L.Loeb, E.Chuang, H.Deshpande; "Turning to the Masters: Motion Capturing Cartoons”
What is Cartoon Capture & Retargeting
• Cartoon Capture– Track the motion From
2D Animation– Represent the motion
& save
• Retargeting– Translate the motion
representation to another output media
![Page 118: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/118.jpg)
C.Bregler, L.Loeb, E.Chuang, H.Deshpande; "Turning to the Masters: Motion Capturing Cartoons”
Digitized video
Key shapes
Cartoon capture
Output corresponding
key shapes
Motion representation retargeting
Output video
Cartoon motion capture & retargeting scheme
![Page 119: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/119.jpg)
C.Bregler, L.Loeb, E.Chuang, H.Deshpande; "Turning to the Masters: Motion Capturing Cartoons”
Modeling Cartoon motion
Digitized video
Key shapes
Cartoon capture
Output corresponding
key shapes
Motion representation retargeting
Output video
![Page 120: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/120.jpg)
C.Bregler, L.Loeb, E.Chuang, H.Deshpande; "Turning to the Masters: Motion Capturing Cartoons”
Modeling Cartoon motion
• Two types of deformations– Affine deformation
– Key shape deformation
![Page 121: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/121.jpg)
C.Bregler, L.Loeb, E.Chuang, H.Deshpande; "Turning to the Masters: Motion Capturing Cartoons”
Affine Deformation
• Affine parameters
Sdaa
daaSwarpV
y
x
43
21),(
],,,,,[)( 4321 yx ddaaaat
Tiii yxs 1
y
x
![Page 122: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/122.jpg)
C.Bregler, L.Loeb, E.Chuang, H.Deshpande; "Turning to the Masters: Motion Capturing Cartoons”
Key-Shape Deformation
• Sk are the key shapes
kkk
y
xSw
daa
daaSwarpV
43
21),(
3w1w 2w
![Page 123: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/123.jpg)
C.Bregler, L.Loeb, E.Chuang, H.Deshpande; "Turning to the Masters: Motion Capturing Cartoons”
Modeling Cartoon motion
• In total there are 6+K variables that represent the motion
],....,,,,,,,[)( 14321 kyx wwddaaaat
![Page 124: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/124.jpg)
C.Bregler, L.Loeb, E.Chuang, H.Deshpande; "Turning to the Masters: Motion Capturing Cartoons”
Cartoon motion capture
Digitized video
Key shapes
Cartoon capture
Output corresponding
key shapes
Motion representation retargeting
Output video
![Page 125: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/125.jpg)
C.Bregler, L.Loeb, E.Chuang, H.Deshpande; "Turning to the Masters: Motion Capturing Cartoons”
Cartoon motion capture
• contour capture: the input is a sequence of contours
• video capture: the input is the video sequence
![Page 126: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/126.jpg)
C.Bregler, L.Loeb, E.Chuang, H.Deshpande; "Turning to the Masters: Motion Capturing Cartoons”
contour capture
• Two step minimization:– Find Affine parameters
– Find Key-Shape weights
• Iterate
2
1 ),...,,( kSSwarpVErr
2
43
21S
daa
daaVErr
y
xaff
1
43
21 )(
TT
y
x SSSVdaa
daa
2
43
21)( kk
y
xSw
daa
daaVErr
![Page 127: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/127.jpg)
C.Bregler, L.Loeb, E.Chuang, H.Deshpande; "Turning to the Masters: Motion Capturing Cartoons”
Retargeting
Digitized video
Key shapes
Cartoon capture
Output corresponding
key shapes
Motion representation retargeting
Output video
![Page 128: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/128.jpg)
C.Bregler, L.Loeb, E.Chuang, H.Deshpande; "Turning to the Masters: Motion Capturing Cartoons”
Retargeting
• For each Input key-shape an Output key-shape is drawn.
![Page 129: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/129.jpg)
C.Bregler, L.Loeb, E.Chuang, H.Deshpande; "Turning to the Masters: Motion Capturing Cartoons”
Retargeting Process
Key shapes Interpolation
Apply Affine transformation
From motion capture
Retargeted media
Retarget Motion capture
![Page 130: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/130.jpg)
C.Bregler, L.Loeb, E.Chuang, H.Deshpande; "Turning to the Masters: Motion Capturing Cartoons”
Examples
![Page 131: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/131.jpg)
C.Bregler, L.Loeb, E.Chuang, H.Deshpande; "Turning to the Masters: Motion Capturing Cartoons”
Additional constrains & post processing
• Undesirable effects may still appear
• Determine constraints that force the character go through certain position at certain time
• Apply ad-hoc global transformation that fulfill these constraints
![Page 132: Animating (human) motion Presented by: –Yoram Atir –Simon Adar.](https://reader036.fdocuments.in/reader036/viewer/2022062308/56649cf85503460f949c8fe7/html5/thumbnails/132.jpg)
C.Bregler, L.Loeb, E.Chuang, H.Deshpande; "Turning to the Masters: Motion Capturing Cartoons”
Performance
• Quantative performance wasn’t mentioned
• The more complex the motion of the character is, the more key-shapes are needed
• Many of the animations contain jitter, but the overall exaggerated motion dominates