Emotion Transfer for 3D Hand and Full Body Motion Using StarGAN
In this paper, we propose a new data-driven framework for 3D hand and full-body motion emotion transfer. Specifically, we formulate the motion synthesis task as an image-to-image translation problem. By presenting a motion sequence as an image representation, the emotion can be transferred by our fr...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Computers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-431X/10/3/38 |
| _version_ | 1797540412069511168 |
|---|---|
| author | Jacky C. P. Chan Edmond S. L. Ho |
| author_facet | Jacky C. P. Chan Edmond S. L. Ho |
| author_sort | Jacky C. P. Chan |
| collection | DOAJ |
| description | In this paper, we propose a new data-driven framework for 3D hand and full-body motion emotion transfer. Specifically, we formulate the motion synthesis task as an image-to-image translation problem. By presenting a motion sequence as an image representation, the emotion can be transferred by our framework using StarGAN. To evaluate our proposed method’s effectiveness, we first conducted a user study to validate the perceived emotion from the captured and synthesized hand motions. We further evaluate the synthesized hand and full body motions qualitatively and quantitatively. Experimental results show that our synthesized motions are comparable to the captured motions and those created by an existing method in terms of naturalness and visual quality. |
| first_indexed | 2024-03-10T12:59:47Z |
| format | Article |
| id | doaj.art-3314780906894798ad074123ef173e6f |
| institution | Directory Open Access Journal |
| issn | 2073-431X |
| language | English |
| last_indexed | 2024-03-10T12:59:47Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Computers |
| spelling | doaj.art-3314780906894798ad074123ef173e6f2023-11-21T11:34:11ZengMDPI AGComputers2073-431X2021-03-011033810.3390/computers10030038Emotion Transfer for 3D Hand and Full Body Motion Using StarGANJacky C. P. Chan0Edmond S. L. Ho1Department of Computer Science, Hong Kong Baptist University, Hong Kong, ChinaDepartment of Computer and Information Sciences, Northumbria University, Newcastle upon Tyne NE1 8ST, UKIn this paper, we propose a new data-driven framework for 3D hand and full-body motion emotion transfer. Specifically, we formulate the motion synthesis task as an image-to-image translation problem. By presenting a motion sequence as an image representation, the emotion can be transferred by our framework using StarGAN. To evaluate our proposed method’s effectiveness, we first conducted a user study to validate the perceived emotion from the captured and synthesized hand motions. We further evaluate the synthesized hand and full body motions qualitatively and quantitatively. Experimental results show that our synthesized motions are comparable to the captured motions and those created by an existing method in terms of naturalness and visual quality.https://www.mdpi.com/2073-431X/10/3/38hand animationbody motionskeletal motionemotionmotion capturegenerative adversarial network |
| spellingShingle | Jacky C. P. Chan Edmond S. L. Ho Emotion Transfer for 3D Hand and Full Body Motion Using StarGAN Computers hand animation body motion skeletal motion emotion motion capture generative adversarial network |
| title | Emotion Transfer for 3D Hand and Full Body Motion Using StarGAN |
| title_full | Emotion Transfer for 3D Hand and Full Body Motion Using StarGAN |
| title_fullStr | Emotion Transfer for 3D Hand and Full Body Motion Using StarGAN |
| title_full_unstemmed | Emotion Transfer for 3D Hand and Full Body Motion Using StarGAN |
| title_short | Emotion Transfer for 3D Hand and Full Body Motion Using StarGAN |
| title_sort | emotion transfer for 3d hand and full body motion using stargan |
| topic | hand animation body motion skeletal motion emotion motion capture generative adversarial network |
| url | https://www.mdpi.com/2073-431X/10/3/38 |
| work_keys_str_mv | AT jackycpchan emotiontransferfor3dhandandfullbodymotionusingstargan AT edmondslho emotiontransferfor3dhandandfullbodymotionusingstargan |