TAILIEUCHUNG - Learning and transferring motion style using sparse PCA
This exploits Sparse PCA to decompose original motions into smaller components which are learned with particular constraints. The synthesized results are highly precise and smooth motions with its emotion as shown in our experiments. | VNU Journal of Science: Comp. Science & Com. Eng., Vol. 35, No. 1 (2019) 1–10 Learning and transferring motion style using Sparse PCA Do Khac Phong1∗, Nguyen Xuan Thanh1 , Hongchuan Yu2, 1 Faculty of Information Technology, VNU University of Engineering and Technology, No. 144 Xuan Thuy Street, Dich Vong Ward, Cau Giay District, Hanoi, Vietnam 2 National Centre for Computer Animation, Bournemouth University, Talbot Campus, Fern Barrow, Poole, Dorset, BH12 5BB, United Kingdom Abstract Motion style transfer is a primary problem in computer animation, allowing us to convert the motion of an actor to that of another one. Myriads approaches have been developed to perform this task, however, the majority of them are data-driven, which require a large dataset and a time-consuming period for training a model in order to achieve good results. In contrast, we propose a novel method applied successfully for this task in a small dataset. This exploits Sparse PCA to decompose original motions into smaller components which are learned with particular constraints. The synthesized results are highly precise and smooth motions with its emotion as shown in our experiments. Received 07 May 2018, Revised 03 December 2018, Accepted 29 December 2018 Keywords: Sparse PCA, style learning, motion style transfer 1. Introduction their emotions like happy, sad, joy, or so. The precise stylization of human motion to express the state of mind or identity plays a vital role in realistic humanoid animation. Previously, this manual work takes numerous time to generate huge variations of motion data, thereby automating this process is really useful and essential for a bunch of applications such as films, and computer games. Many approaches have been developed The automatically precise stylization of human motion to express mood is a primary role in realistic humanoid animation. Motion style transfer is a primary problem in computer animation, allowing us to convert the motion of an actor to .
đang nạp các trang xem trước
