+ All Categories
Home > Documents > Summary & Homework

Summary & Homework

Date post: 07-Jan-2016
Category:
Upload: randy
View: 26 times
Download: 4 times
Share this document with a friend
Description:
Summary & Homework. Jinxiang Chai. Outline. Motion data process paper summary Presentation tips Homework Paper assignment. Skeleton Model Extraction. Estimate the skeleton model from motion capture data. Motion Data Processing I. Operations on single motion sequence - PowerPoint PPT Presentation
Popular Tags:
35
Summary & Homework Jinxiang Chai
Transcript
Page 1: Summary & Homework

Summary & Homework

Jinxiang Chai

Page 2: Summary & Homework

Outline

Motion data process paper summary

Presentation tips

Homework

Paper assignment

Page 3: Summary & Homework

Skeleton Model Extraction

Estimate the skeleton model from motion capture data

Page 4: Summary & Homework

Motion Data Processing I

Operations on single motion sequence

• Motion warping (cannot satisfy user constraints)

Page 5: Summary & Homework

Motion Data Processing I

Operations on single motion sequence

• Motion warping (cannot satisfy user constraints)

• Motion retargeting (can satisfy user constraints but slow)

Page 6: Summary & Homework

Motion Data Processing I

Operations on single motion sequence

• Motion warping (cannot satisfy user constraints)

• Motion retargeting (can satisfy user constraints but slow)

• Motion edit (can satisfy user constraints and fast)

Page 7: Summary & Homework

Motion Data Processing I

Operations on single motion sequence

• Motion warping (cannot satisfy user constraints)

• Motion retargeting (can satisfy user constraints but slow)

• Motion edit (can satisfy user constraints and fast)

However: does not work for many user-defined constraints

does not utilize spatial-temporal correlation in human motion

Page 8: Summary & Homework

Motion Data Processing I

Operations on single motion sequence

• Motion warping (cannot satisfy user constraints)

• Motion retargeting (can satisfy user constraints but slow)

• Motion edit (can satisfy user constraints and fast)

• Expression cloning (facial data) (cannot satisfy user constraints)

Page 9: Summary & Homework

Motion Data Processing I

Operations on single motion sequence

• Motion warping (cannot satisfy user constraints)

• Motion retargeting (can satisfy user constraints but slow)

• Motion edit (can satisfy user constraints and fast)

• Expression cloning (facial data) (cannot satisfy user constraints)

• Motion synopsis

Page 10: Summary & Homework

Motion Data Processing I

Operations on single motion sequence

• Motion warping (cannot satisfy user constraints)

• Motion retargeting (can satisfy user constraints but slow)

• Motion edit (can satisfy user constraints and fast)

• Expression cloning (facial data) (cannot satisfy user constraints)

• Motion synopsis

• What else?

Page 11: Summary & Homework

Motion Data Processing I

Operations on single motion sequence

• Motion segmentation?

• Motion recognition?

• Motion filtering?

• More operations in facial data

Page 12: Summary & Homework

Motion Data Processing II

Operations between two motion sequence

• Motion style translation

• What else?

Page 13: Summary & Homework

Motion Data Processing II

Operations between two motion sequence

• Motion style translation

• What else?

Page 14: Summary & Homework

Motion Data Processing II

Operations between two motion sequence

• Motion style translation

• Motion interpolation?

Page 15: Summary & Homework

Motion Data Processing III

Operations on multiple motion sequences/database

• Motion data compression

Page 16: Summary & Homework

Motion Data Processing III

Operations on multiple motion sequences/database

• Motion data compression

• What else?

Page 17: Summary & Homework

Motion Data Processing III

Operations on multiple motion sequences/database

• Motion data compression

• Motion Retrieval?

• Motion synthesis?

Page 18: Summary & Homework

Presentation Tips

Choose right background• Use blue or black or dark colors

Focus on important things• Always talk about what, why, and how

• Detailize the most important technical content

• Always talk about the limitations of the paper

How to deal with equations• Avoid using too many equations

• Talk about the intuition of the equations

• Explain each term of the equations

Page 19: Summary & Homework

Presentation Tips (Cont.)

Choose the right background• Use dark colors (blue or black)

Be consistent• Font type, size, color, bullets, figure captions etc.

Use short & concise sentences• Do not copy & paste from the paper

• Use images, diagrams, figures, videos to demonstrate ideas

Page 20: Summary & Homework

Presentation Tips (Cont.)

Play videos• Explain each video

• Move the mouse away from the window

Page 21: Summary & Homework

Example Slides

Page 22: Summary & Homework

Goal: everyone can generate and control human motion easily and quickly

Online animation control

Interfaces for Controlling Human Motion

Page 23: Summary & Homework

Applications: Online Animation

Performance-based facial animation for home use

Tiger Woods PGA Tour 2005

Mike Tyson Heavyweight Boxing

Friday Night 3D Bowling

Teleconferencing (from BT)

Xbox Outlaw Tennis

Multi-user Virtual Worlds

Virtual Poker Room

Virtual Presenter

Page 24: Summary & Homework

Reordering motion clip [Lee et al. SIG02, Kovar et al. SIG02, Pullen & Bregler SIG02, Arikan et al. SIG03]

Learning model from human motion [Brand & Hertzmann SIG00, Li et al. SIG02]

Interpolating motions [Rose et al. CG&A98, Kovar et al. SIG04]

Animation from Mocap Data

Page 25: Summary & Homework

Video Analysis

Overview

Online motion synthesis

Online local modeling

Low-dimensional control signals

Preprocessedmotion capture

dataPreprocessed

motion capturedata

Online local models

Page 26: Summary & Homework

Online Motion Optimization

2

21

21 ~~2~)(minarg tttttttttt

Tt

Ttw qqpwUcwfwUUw

t

Optimizing a nonlinear function in about 7 dimensional space wt :

Control term

Smoothness term

Pose prior term

1~q tq

~

tc~…

1~c

?

Page 27: Summary & Homework

Outline

Motion data paper summary

Presentation tips

Homework

Paper assignment

Page 28: Summary & Homework

Dimensionality reduction using PCA

tttt wUpq ~Current pose Mean pose

Eigen-poses Low-dimensional space

Linear model:

Mean pose

Eigen-poses

Dim(wt)?

Linear Dimensionality Reduction

Page 29: Summary & Homework

Linear Dimensionality Reduction

0 5 10 15 20 25 30 35 40 45 500

5

10

15

20

25

30

Ave

rage

rec

on

stru

ctio

n e

rro

r(d

egre

e p

er jo

int

ang

le)

A large heterogeneous database (1 hour of data)

PCA (38D for error<1o)

Number of dimensions

Page 30: Summary & Homework

Reconstruction Error Curve

0 10 20 30 40 50 600

0.5

1

1.5

2

2.5

Ave

rage

rec

on

stru

ctio

n e

rro

r(d

egre

e p

er jo

int

ang

le)

A large database

Number of dimensions of Wt

tttt wUpq ~

Page 31: Summary & Homework

Minimal Dimensionality

0 10 20 30 40 50 600

0.5

1

1.5

2

2.5

Ave

rage

rec

on

stru

ctio

n e

rro

r(d

egre

e p

er jo

int

ang

le)

A large database

Number of dimensions of Wt

tttt wUpq ~

7

0.8

tttt wUpq ~

56 dim 7 dim

Page 32: Summary & Homework

Videos

Two Animation videos rendered by Maya• Original mocap sequence

• Reconstructed mocap sequence

Page 33: Summary & Homework

Startup Codes & Data

Motion capture data (.amc files and .asf file)

A skinned character model

Visualize amc/asf file• Read asf/amc file

• Visualize mocap data

• Forward kinematics

Matlab codes• Read and write .amc file

Page 34: Summary & Homework

Softwares

Maya• To be installed in Rm 220, HRBB

• Render each frame based on mocap data and character model

• Instruction on how to render animation

Adobe Premier • Installed in Rm 220, HRBB

• Making video from image sequences

Page 35: Summary & Homework

Outline

Motion data paper summary

Presentation tips

Homework

Paper assignment


Recommended