Learning and transferring motion style using Sparse PCA
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 perio...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
H. : ĐHQGHN
2019
|
| Subjects: | |
| Online Access: | http://repository.vnu.edu.vn/handle/VNU_123/64776 https:// doi.org/10.25073/2588-1086/vnucsce.206 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Vietnam National University, Hanoi |
| Language: | English |
| id |
oai:112.137.131.14:VNU_123-64776 |
|---|---|
| record_format |
dspace |
| spelling |
oai:112.137.131.14:VNU_123-647762019-07-01T08:23:13Z Learning and transferring motion style using Sparse PCA Do, Khac Phong Nguyen, Xuan Thanh Yu, Hongchuan Sparse PCA style learning motion style transfer 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 2019-07-01T08:23:13Z 2019-07-01T08:23:13Z 2019 Article Do, K. P., et al. (2019). Learning and transferring motion style using Sparse PCA. Journal of Science: Comp. Science & Com. Eng., Vol. 35, No. 1 (2019) 1–10. 2588-1086 http://repository.vnu.edu.vn/handle/VNU_123/64776 https:// doi.org/10.25073/2588-1086/vnucsce.206 en Journal of Science: Comp. Science & Com. Eng.; application/pdf H. : ĐHQGHN |
| institution |
Vietnam National University, Hanoi |
| building |
VNU Library & Information Center |
| country |
Vietnam |
| collection |
VNU Digital Repository |
| language |
English |
| topic |
Sparse PCA style learning motion style transfer |
| spellingShingle |
Sparse PCA style learning motion style transfer Do, Khac Phong Nguyen, Xuan Thanh Yu, Hongchuan Learning and transferring motion style using Sparse PCA |
| description |
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 |
| format |
Article |
| author |
Do, Khac Phong Nguyen, Xuan Thanh Yu, Hongchuan |
| author_facet |
Do, Khac Phong Nguyen, Xuan Thanh Yu, Hongchuan |
| author_sort |
Do, Khac Phong |
| title |
Learning and transferring motion style using Sparse PCA |
| title_short |
Learning and transferring motion style using Sparse PCA |
| title_full |
Learning and transferring motion style using Sparse PCA |
| title_fullStr |
Learning and transferring motion style using Sparse PCA |
| title_full_unstemmed |
Learning and transferring motion style using Sparse PCA |
| title_sort |
learning and transferring motion style using sparse pca |
| publisher |
H. : ĐHQGHN |
| publishDate |
2019 |
| url |
http://repository.vnu.edu.vn/handle/VNU_123/64776 https:// doi.org/10.25073/2588-1086/vnucsce.206 |
| _version_ |
1680962742602694656 |