Home      Publications      People      Contact      中文  
Realtime Style Transfer for Unlabeled Heterogeneous Human Motion
ACM Transactions on Graphics (SIGGRAPH), 2015

Shihong Xia 1   Congyi Wang 1  Jinxiang Chai 2   Jessica Hodgins 3

1 Institute of Computing Technology, CAS  2 Texas A&M University  3 Carnegie Mellon University

This paper presents a novel solution for realtime generation of stylistic human motion that automatically transforms unlabeled,heterogeneous motion data into new styles. The key idea of our approach is an online learning algorithm that automatically constructs a series of local mixtures of autoregressive models (MAR) to capture the complex relationships between styles of motion. We construct local MAR models on the fly by searching for the closest examples of each input pose in the database. Once the model parameters are estimated from the training data, the model adapts the current pose with simple linear transformations. In addition, we introduce an efficient local regression model to predict the timings of synthesized poses in the output style. We demonstrate the power of our approach by transferring stylistic human motion for a wide variety of actions, including walking,running, punching, kicking, jumping and transitions between those behaviors. Our method achieves superior performance in a comparison against alternative methods. We have also performed experiments to evaluate the generalization ability of our data-driven model as well as the key components of our system.
Obtaining the data and source code

On request, we make all the algorithm relative data and source code available for scientific purposes. To obtain a copy,please send an email to XSH AT ICT DOT AC DOT CN, stating
    1.name, title or position, and institution or affiliation;
    2.intended use of the data, further information about you and your work;
    Please understand that we can only provide the data to you if you are a senior project manager or senior researcher at your institution.
    We would also like to ask you to acknowledge the origin of the data by citing the above paper in any publication using the human motion capture data or source code.Please note that you are not allowed to pass the data to a third party without prior permission.


Realtime Style Transfer for Unlabeled Heterogeneous Human Motion. ACM Transactions on Graphics, 2015 [ PDF 1,914KB] [ PPT 117,436KB] [ Video 75,541KB] [ SupplementalMaterial 1,636KB] [ EvaluationVideo 109,855KB] [ PaperFast Forward Video 11,065KB]