Motion Capture Assisted Animation: Texturing and

Synthesis

SIGGRAPH ’02

Speaker: Alvin

Date:23 August 2004

Alivn/GAME Lab./CSIE/NDHU

Motion Capture Assisted Animation: Texturing and Synthesis

2

Outline

Introduction

Framework

Results

Conclusions and Future Work

Alivn/GAME Lab./CSIE/NDHU

Motion Capture Assisted Animation: Texturing and Synthesis

3

Introduction

Create a method that allows an artist low-level control of the motion

Combine the strengths of keyframe animation with those of mocap

Alivn/GAME Lab./CSIE/NDHU

Motion Capture Assisted Animation: Texturing and Synthesis

4

Introduction (cont.)

“Sketch” an animation by keyframingAnimate only a few degrees of freedom

Set few keyframes

“Enhance” the result with mocap dataSynthesize missing degrees of freedom

Texture keyframed degrees of freedom

Alivn/GAME Lab./CSIE/NDHU

Motion Capture Assisted Animation: Texturing and Synthesis

5

Keyframing vs. MocapKeyframing vs. Mocap

Keyframing

Mocap

DisadvantagesAdvantages

•Control•Intuitive

•No control•Not intuitive

•Detail hard•Many DOF

•Detail easy•All DOF

Alivn/GAME Lab./CSIE/NDHU

Motion Capture Assisted Animation: Texturing and Synthesis

6

Keyframe vs. MoCap

Alivn/GAME Lab./CSIE/NDHU

Motion Capture Assisted Animation: Texturing and Synthesis

7

Correlation

Alivn/GAME Lab./CSIE/NDHU

Motion Capture Assisted Animation: Texturing and Synthesis

8

Framework

Choosing Matching Angles

Frequency Analysis

Segmentation

Matching

Path Finding

Joining

Alivn/GAME Lab./CSIE/NDHU

Motion Capture Assisted Animation: Texturing and Synthesis

9

Choosing Matching AnglesLeft 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

Alivn/GAME Lab./CSIE/NDHU

Motion Capture Assisted Animation: Texturing and Synthesis

10

Frequency Analysis

Laplacian Pyramid Decomposition

Alivn/GAME Lab./CSIE/NDHU

Motion Capture Assisted Animation: Texturing and Synthesis

11

Segmentation

Alivn/GAME Lab./CSIE/NDHU

Motion Capture Assisted Animation: Texturing and Synthesis

12

Matching

KeyframedFragment

Motion Capture Data

Alivn/GAME Lab./CSIE/NDHU

Motion Capture Assisted Animation: Texturing and Synthesis

13

Matching (cont.)

Alivn/GAME Lab./CSIE/NDHU

Motion Capture Assisted Animation: Texturing and Synthesis

14

Matching (cont.)

Hip Angle (Matching Angle)

Spine Angle (For Synthesis)

Alivn/GAME Lab./CSIE/NDHU

Motion Capture Assisted Animation: Texturing and Synthesis

15

Matching and Synthesis

Low frequency hip angle data (a matching angle)

Spine angle data to be synthesized

Alivn/GAME Lab./CSIE/NDHU

Motion Capture Assisted Animation: Texturing and Synthesis

16

Path FindingA

ngle

in d

egre

es

Time

Alivn/GAME Lab./CSIE/NDHU

Motion Capture Assisted Animation: Texturing and Synthesis

17

JoiningA

ngle

in d

egre

es

Time

Alivn/GAME Lab./CSIE/NDHU

Motion Capture Assisted Animation: Texturing and Synthesis

18

Path Finding

Alivn/GAME Lab./CSIE/NDHU

Motion Capture Assisted Animation: Texturing and Synthesis

19

Joining

Alivn/GAME Lab./CSIE/NDHU

Motion Capture Assisted Animation: Texturing and Synthesis

20

Smoothing

Alivn/GAME Lab./CSIE/NDHU

Motion Capture Assisted Animation: Texturing and Synthesis

21

Smoothing (cont.)

Blend Function

The data s after smoothing is

Alivn/GAME Lab./CSIE/NDHU

Motion Capture Assisted Animation: Texturing and Synthesis

22

Result

Watch the demo movie file.

Alivn/GAME Lab./CSIE/NDHU

Motion Capture Assisted Animation: Texturing and Synthesis

23

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

Alivn/GAME Lab./CSIE/NDHU

Motion Capture Assisted Animation: Texturing and Synthesis

24

Conclusions and Future Work

Combine the advantages of both methods

Allow the user control an initial rough animation with keyframes

Fill in missing DOFs and detail using the information in motion capture data

Direct incorporation of hard constraints

Fundamental units of motion

Alivn/GAME Lab./CSIE/NDHU

Motion Capture Assisted Animation: Texturing and Synthesis

25

Evaluation Form

論文簡報部份完整性介紹 (4)

系統性介紹 (4)

表達能力 (3)

投影片製作 (4)

論文審閱部分瞭解論文內容 (4)

結果正確性與完整性 (4)

原創性與重要性 (4)

讀後啟發與應用：

The method using the correlative relationship of the joints to synthesisthe other DOFs can be used in my research.