- For Attendees
- For Presenters
- For Volunteers
- Seoul
- For Exhibitors & Sponsors
- Registration
- For the Media
Courses
Introduction to Data-Driven Animation: Programming With Motion Capture
Tuesday, 14 December | 9:00 pm - 10:45 pm | Room 308A
Data-driven animation using motion-capture data has become a standard practice in character animation. A number of techniques have been developed to add flexibility on captured human motion data by editing joint trajectories, warping motion paths, blending a family of parameterized motions, splicing motion segments, and adapting motion to new characters and environments.
Even with the abundance of motion-capture data and the popularity of data-driven animation techniques, programming with motion capture-data is still not easy. A single clip of motion data encompasses a lot of heterogeneous information including joint angles, the position and orientation of the skeletal root, their temporal trajectories, and a number of coordinate systems. Due to this complexity, even simple operations on motion data, such as linear interpolation, are rarely described as succinct mathematical equations in research papers.
This course provides not only a solid mathematical background, but also a practical guide to programming with motion-capture data. It begins with a brief review of affine geometry and coordinate-invariant (conventionally called coordinate-free) geometric programming, which generalizes incrementally to deal with three-dimensional rotations/orientations, the poses of an articulated figure, and full-body motion data. Then it identifies a collection of coordinate-invariant operations on full-body motion data and their object-oriented implementation. Finally, it explains the practical use of this programming framework in a variety of contexts ranging from data-driven manipulation and interpolation to state-of-the-art biped locomotion control.
Level
Beginner
Intended Audience
Mainly beginners who are interested in data-driven animation and motion capture, and experienced programmers who need to animate articulated characters. Advanced researchers in computer animation may also benefit from the mathematical framework and programming style presented in the course.
Presentation Language
Presented in English / 영어로 발표 됨
Prerequisites
Knowledge of undergraduate-level computer graphics.
Syllabus
Introduction and Overview
Data-driven animation using motion-capture data
Why is it difficult to do programming with motion-capture data?
Course overview
Coordinate-Invariant Programming with Points and Vectors
What is coordinate-invariant geometric programming?
Affine geometry
Coordinate-invariant operations between points and vectors
Programming with Orientations and Rotations
Representing orientations and rotations
Analogy between points/vectors and orientations/rotations
Coordinate-invariant operations with orientations and rotations
Linear combination of rotations
Affine combination of orientations
Programming with Motion Capture Data
Representing the poses and pose displacements of an articulated figure
Motion data and displacements
Coordinate-invariant programming with motion data
Practical Examples
Distance measure
Hierarchical displacement mapping
Interpolation and transitioning
Style transfer
Feedback control for physically based biped locomotion
Jehee Lee
Seoul National University
Instructor Bios
Jehee Lee
Jehee Lee is an associate professor at Seoul National University. He received his BS, MS, and PhD in computer science from Korea Advanced Institute of Science and Technology in 1993, 1995, and 2000, respectively. He leads the SNU Movement Research Laboratory, where his research interests in computer graphics and animation are focused on developing new ways of understanding, representing, and animating human movement. This involves full-body motion analysis and synthesis, biped control and simulation, motion capture, motion planning, data-driven and physically based techniques, interactive avatar control, crowd simulation, and facial animation.