Constraint-based Motion Optimization Using A Statistical Dynamic Model

Space-time optimization using a statistical dynamic model


Project description

We present a technique for generating animation from a variety of user-defined constraints. We pose constraint-based motion synthesis as a maximum a posterior (MAP) problem and develop an optimization framework that generates natural motion satisfying user constraints. The system automatically learns a statistical dynamic model from motion capture data and then enforces it as a motion prior. This motion prior, together with user-defined constraints, comprises a trajectory optimization problem. Solving this problem in the low-dimensional space yields optimal natural motion that achieves the goals specified by the user.

We demonstrate the effectiveness of this approach in two domains: human body animation and facial animation. We show that the system can generate natural-looking animation from key-frame constraints, key-trajectory constraints, and a combination of these two constraints. For example, the user can generate a walking animation from a small set of key frames and foot contact constraints. The user can also specify a small set of key trajectories for the root, hands and feet positions to generate a realistic jumping motion. The system can generate motions for a character whose skeletal model is markedly different from those of the subjects in the database. We also show that the system can use a statistical dynamic model learned from a normal walking sequence to create new motion such as walking on a slope.


  Constraint-based Motion Optimization Using A Statistical Dynamic Model, ACM Transactions on Graphics (SIGGRAPH 2007)

PDF (17.5M); final video (26Mb mov clip with audio)

Related projects

Face Poser: Interactive Facial Expression Modeling Using Model Priors 

ACM SIGGRAPH/Eurographics Symposium on Computer Animation  (SCA 2007), In press.

Performance Animation from Low-dimensional Control Signals

ACM Transactions on Graphics (SIGGRAPH 2005)

      Vision-based Control of 3D Facial Animation
      ACM SIGGRAPH/Eurographics Symposium on Computer Animation (SCA 2003)
      Interactive Control of Avatars Animated with Human Motion Data

ACM Transactions on Graphics (SIGGRAPH 2002)


Jinxiang Chai
Last Updated: July
12, 2007