MGF: Mixed Gaussian Flow for Diverse Trajectory Prediction
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_ | 1866912188527017984 |
|---|---|
| author | Chen, Jiahe Cao, Jinkun Lin, Dahua Kitani, Kris Pang, Jiangmiao |
| author_facet | Chen, Jiahe Cao, Jinkun Lin, Dahua Kitani, Kris Pang, Jiangmiao |
| contents | To predict future trajectories, the normalizing flow with a standard Gaussian prior suffers from weak diversity. The ineffectiveness comes from the conflict between the fact of asymmetric and multi-modal distribution of likely outcomes and symmetric and single-modal original distribution and supervision losses. Instead, we propose constructing a mixed Gaussian prior for a normalizing flow model for trajectory prediction. The prior is constructed by analyzing the trajectory patterns in the training samples without requiring extra annotations while showing better expressiveness and being multi-modal and asymmetric. Besides diversity, it also provides better controllability for probabilistic trajectory generation. We name our method Mixed Gaussian Flow (MGF). It achieves state-of-the-art performance in the evaluation of both trajectory alignment and diversity on the popular UCY/ETH and SDD datasets. Code is available at https://github.com/mulplue/MGF. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_12238 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MGF: Mixed Gaussian Flow for Diverse Trajectory Prediction Chen, Jiahe Cao, Jinkun Lin, Dahua Kitani, Kris Pang, Jiangmiao Computer Vision and Pattern Recognition To predict future trajectories, the normalizing flow with a standard Gaussian prior suffers from weak diversity. The ineffectiveness comes from the conflict between the fact of asymmetric and multi-modal distribution of likely outcomes and symmetric and single-modal original distribution and supervision losses. Instead, we propose constructing a mixed Gaussian prior for a normalizing flow model for trajectory prediction. The prior is constructed by analyzing the trajectory patterns in the training samples without requiring extra annotations while showing better expressiveness and being multi-modal and asymmetric. Besides diversity, it also provides better controllability for probabilistic trajectory generation. We name our method Mixed Gaussian Flow (MGF). It achieves state-of-the-art performance in the evaluation of both trajectory alignment and diversity on the popular UCY/ETH and SDD datasets. Code is available at https://github.com/mulplue/MGF. |
| title | MGF: Mixed Gaussian Flow for Diverse Trajectory Prediction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.12238 |