Topics on Computer Graphics (4541.762)

(Data-Driven Animation)

 

Spring 2004

 

 

Description

 

This course is intended to provide key ideas in data-driven animation.

The goal of data-driven animation is to create the behavior of animated characters from a collection of motion data. We will discuss the fundamental ideas for the first six weeks and then survey the current state of the art.

 

Instructor

Jehee Lee

Office: 302-325

Phone: 880-1845

 

Class hours

Monday and Wednesday 1:00-2:15pm

 

Classroom

Building 302, Room 308

 

Pre-requisites

Undergraduate computer graphics

Programming skills for C or C++

Programming skills for OpenGL or DirectX are recommended, but not required

 

Grading policy

 

Classroom presentation: 20 %

Programming assignments: 40%

Quiz & exam: 40%

 

Schedule

Week 1

3 / 1

 

3 / 3

 Course Introduction

 History of motion capture

  • 모션 캡쳐의 과거, 현재, 그리고 미래 [reading]

Week 2

3 / 8

 Coordinate-free geometric programming

3 / 10

 Transformation

  • Chap 3 of the course note written by Tony DeRose.

  • Hw #1 out

Week 3

3 / 15

 Splines

  • Hw #1 hand in

3 / 17

 Rotation and orientation: Fundamentals

Week 4

3 / 22

 Rotation and orientation: A coordinate free perspective

  • Hw #2 out

3 / 24

 Rotation and orientation: Affine Combination

Week 5

3 / 29

 Solving linear systems

  • Chap 2 of Numerical Recipes. The book is available on-line at http://www.nr.com

  • Hw #2 hand in

3 / 31

 Solving overdetermined and underdetermined linear systems

Week 6

4 / 5

 No class (식목일)

4 / 7

 Kinematics

Week 7

4 / 12

 Inverse kinematics

4 / 14

 Quiz

Week 8

4 / 19

 Geometric methods

4 / 21

 Transition and smooth concatenation

  • Motion warping, A. P. Witkin and Z. Popovic, Siggraph 95.

  • Hw #3 presentation

  • Programming assignment #1 out

Week 9

4 / 26

 Constraint-based methods

4 / 28

 Interpolation and blending

Week 10

5 / 3

 Radial-basis functions

5 / 5

 No class (어린이날)

Week 11

5 / 10

 RBF Interpolation

  • Programming assignment #2 out

5 / 12

 Signal processing methods]

Week 12

5 / 17

 Multiresolution analysis

5 / 19

 Graph representation

Week 13

5 / 24

 Computer puppetry

5 / 26

 No class (석가탄신일)

Week 14

5 / 31

 Animation by example

  • Guest lecturer: Prof. Michael Gleicher  will give a talk.

  • Bld 302, Room 619 (1:00 pm)

Abstract

The motion of animated human characters is notoriously difficult to
create. Motion synthesis methods must achieve expressiveness, subtlety
and realism. The current techniques for creating such quality motions,
such as capturing it by observing real performers, can achieve these
qualities in short, specific clips of motion. However, while these clips
provide examples of what a character can do, a set of clips by itself
does not provide sufficient flexibility to animate all of the things we
might require of a character. We need methods that are capable of
synthesizing new motions that have the qualities of the examples.

In this talk, I will survey our efforts to create high-quality motion
for animation in a flexible manner. I will describe four recent projects
from our group:

- Motion Graphs - an approach to creating new motions by assembling
pieces of existing motions;

- Snap Together Motion - an approach to using Motion Graphs in
interactive systems;

- Registration Curves - an approach to creating new motions that are
combinations (blends) of existing motions;

- Match Webs - an approach to searching and organizing a large database
of motions so that it can be used for synthesis tasks.
 

6 / 2

 State-space search (A*-algorithm)

  • Programming Assignment #3 out

Week 15

6 / 7

 Dynamic programming: fundamentals

  • Min Gyu Choi, Jehee Lee, Sung Yong Shin, Planning Biped Locomotion Using Motion Capture Data and Probabilistic Roadmaps, ACM Transactions on Graphics, volume 22, number 2, 182-203, 2003.

    PDF (1.5M)

  • Arikan, Forsyth, and O'Brien, Motion synthesis from anotations, Siggraph 2003.

6 / 9

 Dynamic programming: applications