Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909163169251328 |
|---|---|
| author | Jeong, Jaewoo Park, Daehee Yoon, Kuk-Jin |
| author_facet | Jeong, Jaewoo Park, Daehee Yoon, Kuk-Jin |
| contents | Human pose forecasting garners attention for its diverse applications. However, challenges in modeling the multi-modal nature of human motion and intricate interactions among agents persist, particularly with longer timescales and more agents. In this paper, we propose an interaction-aware trajectory-conditioned long-term multi-agent human pose forecasting model, utilizing a coarse-to-fine prediction approach: multi-modal global trajectories are initially forecasted, followed by respective local pose forecasts conditioned on each mode. In doing so, our Trajectory2Pose model introduces a graph-based agent-wise interaction module for a reciprocal forecast of local motion-conditioned global trajectory and trajectory-conditioned local pose. Our model effectively handles the multi-modality of human motion and the complexity of long-term multi-agent interactions, improving performance in complex environments. Furthermore, we address the lack of long-term (6s+) multi-agent (5+) datasets by constructing a new dataset from real-world images and 2D annotations, enabling a comprehensive evaluation of our proposed model. State-of-the-art prediction performance on both complex and simpler datasets confirms the generalized effectiveness of our method. The code is available at https://github.com/Jaewoo97/T2P. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_05218 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning Jeong, Jaewoo Park, Daehee Yoon, Kuk-Jin Computer Vision and Pattern Recognition Artificial Intelligence Human pose forecasting garners attention for its diverse applications. However, challenges in modeling the multi-modal nature of human motion and intricate interactions among agents persist, particularly with longer timescales and more agents. In this paper, we propose an interaction-aware trajectory-conditioned long-term multi-agent human pose forecasting model, utilizing a coarse-to-fine prediction approach: multi-modal global trajectories are initially forecasted, followed by respective local pose forecasts conditioned on each mode. In doing so, our Trajectory2Pose model introduces a graph-based agent-wise interaction module for a reciprocal forecast of local motion-conditioned global trajectory and trajectory-conditioned local pose. Our model effectively handles the multi-modality of human motion and the complexity of long-term multi-agent interactions, improving performance in complex environments. Furthermore, we address the lack of long-term (6s+) multi-agent (5+) datasets by constructing a new dataset from real-world images and 2D annotations, enabling a comprehensive evaluation of our proposed model. State-of-the-art prediction performance on both complex and simpler datasets confirms the generalized effectiveness of our method. The code is available at https://github.com/Jaewoo97/T2P. |
| title | Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2404.05218 |