Human Motion Synthesis_ A Diffusion Approach for Motion Stitching and In-Betweening
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909311248105472 |
|---|---|
| author | Adewole, Michael Giwa, Oluwaseyi Nerrise, Favour Osifeko, Martins Oyedeji, Ajibola |
| author_facet | Adewole, Michael Giwa, Oluwaseyi Nerrise, Favour Osifeko, Martins Oyedeji, Ajibola |
| contents | Human motion generation is an important area of research in many fields. In this work, we tackle the problem of motion stitching and in-betweening. Current methods either require manual efforts, or are incapable of handling longer sequences. To address these challenges, we propose a diffusion model with a transformer-based denoiser to generate realistic human motion. Our method demonstrated strong performance in generating in-betweening sequences, transforming a variable number of input poses into smooth and realistic motion sequences consisting of 75 frames at 15 fps, resulting in a total duration of 5 seconds. We present the performance evaluation of our method using quantitative metrics such as Frechet Inception Distance (FID), Diversity, and Multimodality, along with visual assessments of the generated outputs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_06791 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Human Motion Synthesis_ A Diffusion Approach for Motion Stitching and In-Betweening Adewole, Michael Giwa, Oluwaseyi Nerrise, Favour Osifeko, Martins Oyedeji, Ajibola Computer Vision and Pattern Recognition Human-Computer Interaction Machine Learning Human motion generation is an important area of research in many fields. In this work, we tackle the problem of motion stitching and in-betweening. Current methods either require manual efforts, or are incapable of handling longer sequences. To address these challenges, we propose a diffusion model with a transformer-based denoiser to generate realistic human motion. Our method demonstrated strong performance in generating in-betweening sequences, transforming a variable number of input poses into smooth and realistic motion sequences consisting of 75 frames at 15 fps, resulting in a total duration of 5 seconds. We present the performance evaluation of our method using quantitative metrics such as Frechet Inception Distance (FID), Diversity, and Multimodality, along with visual assessments of the generated outputs. |
| title | Human Motion Synthesis_ A Diffusion Approach for Motion Stitching and In-Betweening |
| topic | Computer Vision and Pattern Recognition Human-Computer Interaction Machine Learning |
| url | https://arxiv.org/abs/2409.06791 |