Abstract
Traditionally, style transfer methods have extracted style element from user-provided "Style motion"and content element from "Content motion", and combining these two elements to achieve transferred style in the content motion. In the process, they attempted to separate movements into style and content elements in a binary way. However, ambiguity exists between the definitions of style and content. An action of crossing your arms when you are angry (style) while walking (content) is not clearly categorized as either style or content. In this work we define "Gesture Style"referring to a short-term action revealing style (not content) in a motion sequence. Crossing arms in the example falls in Gesture Style, as it represents anger but is performed for short time. We propose a new style transfer method with Gesture Style Generator. It transfers style to the output motion in the conventional style transfer manner while also incorporating generated Gesture Style.
| Original language | English |
|---|---|
| Title of host publication | Proceedings - SIGGRAPH Asia 2024 Posters, SA 2024 |
| Editors | Stephen N. Spencer |
| Publisher | Association for Computing Machinery, Inc |
| ISBN (Electronic) | 9798400711381 |
| DOIs | |
| Publication status | Published - 3 Dec 2024 |
| Event | 2024 SIGGRAPH Asia 2024 Posters, SA 2024 - Tokyo, Japan Duration: 3 Dec 2024 → 6 Dec 2024 |
Publication series
| Name | Proceedings - SIGGRAPH Asia 2024 Posters, SA 2024 |
|---|
Conference
| Conference | 2024 SIGGRAPH Asia 2024 Posters, SA 2024 |
|---|---|
| Country/Territory | Japan |
| City | Tokyo |
| Period | 3/12/24 → 6/12/24 |
Bibliographical note
Publisher Copyright:© 2024 Copyright held by the owner/author(s).
Keywords
- Content
- Motion generation
- Motion style transfer
- Style
Fingerprint
Dive into the research topics of 'Style Transfer with Gesture Style Generator'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver