Co-Speech Gesture and Facial Expression Generation for Non-Photorealistic 3D Characters
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912440212520960 |
|---|---|
| author | Omine, Taisei Kawabata, Naoyuki Homma, Fuminori |
| author_facet | Omine, Taisei Kawabata, Naoyuki Homma, Fuminori |
| contents | With the advancement of conversational AI, research on bodily expressions, including gestures and facial expressions, has also progressed. However, many existing studies focus on photorealistic avatars, making them unsuitable for non-photorealistic characters, such as those found in anime. This study proposes methods for expressing emotions, including exaggerated expressions unique to non-photorealistic characters, by utilizing expression data extracted from comics and dialogue-specific semantic gestures. A user study demonstrated significant improvements across multiple aspects when compared to existing research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_16159 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Co-Speech Gesture and Facial Expression Generation for Non-Photorealistic 3D Characters Omine, Taisei Kawabata, Naoyuki Homma, Fuminori Computer Vision and Pattern Recognition I.2.10 With the advancement of conversational AI, research on bodily expressions, including gestures and facial expressions, has also progressed. However, many existing studies focus on photorealistic avatars, making them unsuitable for non-photorealistic characters, such as those found in anime. This study proposes methods for expressing emotions, including exaggerated expressions unique to non-photorealistic characters, by utilizing expression data extracted from comics and dialogue-specific semantic gestures. A user study demonstrated significant improvements across multiple aspects when compared to existing research. |
| title | Co-Speech Gesture and Facial Expression Generation for Non-Photorealistic 3D Characters |
| topic | Computer Vision and Pattern Recognition I.2.10 |
| url | https://arxiv.org/abs/2506.16159 |