Animate your avatar: learning conditional human motion prior
This research project focuses on the concept of virtual humans and aims to enable natural language control of 3D avatars, allowing them to perform human-like movements that are coherent with their surrounding environment. To achieve this goal, the project proposes to learn a "conditional"...
| Huvudupphovsman: | |
|---|---|
| Övriga upphovsmän: | |
| Materialtyp: | Final Year Project (FYP) |
| Språk: | English |
| Publicerad: |
Nanyang Technological University
2023
|
| Ämnen: | |
| Länkar: | https://hdl.handle.net/10356/165971 |
| _version_ | 1826119095950508032 |
|---|---|
| author | Singh, Ananya |
| author2 | Liu Ziwei |
| author_facet | Liu Ziwei Singh, Ananya |
| author_sort | Singh, Ananya |
| collection | NTU |
| description | This research project focuses on the concept of virtual humans and aims to enable natural language control of 3D avatars, allowing them to perform human-like movements that are coherent with their surrounding environment. To achieve this goal, the project proposes to learn a "conditional" human motion prior that takes into account scene information and/or language descriptions. This approach is intended to generate more coherent and meaningful human-like motions that are better suited to specific scenarios and objectives. The potential applications of this research include gaming, virtual avatars, and the Metaverse. The project employs a two-stage approach that combines language-conditioned human motion generation and physics-based character control techniques to generate diverse and physically plausible human motions in a physical world from language descriptions. The results of the project demonstrate the effectiveness of this approach in terms of motion diversity, faithfulness to the language description, and physical plausibility. |
| first_indexed | 2024-10-01T04:54:28Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/165971 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:54:28Z |
| publishDate | 2023 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1659712023-04-21T15:37:33Z Animate your avatar: learning conditional human motion prior Singh, Ananya Liu Ziwei School of Computer Science and Engineering ziwei.liu@ntu.edu.sg Engineering::Computer science and engineering This research project focuses on the concept of virtual humans and aims to enable natural language control of 3D avatars, allowing them to perform human-like movements that are coherent with their surrounding environment. To achieve this goal, the project proposes to learn a "conditional" human motion prior that takes into account scene information and/or language descriptions. This approach is intended to generate more coherent and meaningful human-like motions that are better suited to specific scenarios and objectives. The potential applications of this research include gaming, virtual avatars, and the Metaverse. The project employs a two-stage approach that combines language-conditioned human motion generation and physics-based character control techniques to generate diverse and physically plausible human motions in a physical world from language descriptions. The results of the project demonstrate the effectiveness of this approach in terms of motion diversity, faithfulness to the language description, and physical plausibility. Bachelor of Science in Data Science and Artificial Intelligence 2023-04-17T07:00:15Z 2023-04-17T07:00:15Z 2023 Final Year Project (FYP) Singh, A. (2023). Animate your avatar: learning conditional human motion prior. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/165971 https://hdl.handle.net/10356/165971 en SCSE22-0197 application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering Singh, Ananya Animate your avatar: learning conditional human motion prior |
| title | Animate your avatar: learning conditional human motion prior |
| title_full | Animate your avatar: learning conditional human motion prior |
| title_fullStr | Animate your avatar: learning conditional human motion prior |
| title_full_unstemmed | Animate your avatar: learning conditional human motion prior |
| title_short | Animate your avatar: learning conditional human motion prior |
| title_sort | animate your avatar learning conditional human motion prior |
| topic | Engineering::Computer science and engineering |
| url | https://hdl.handle.net/10356/165971 |
| work_keys_str_mv | AT singhananya animateyouravatarlearningconditionalhumanmotionprior |