1st Place Solution of Multiview Egocentric Hand Tracking Challenge ECCV2024
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912063811485696 |
|---|---|
| author | Zou, Minqiang Lv, Zhi Jin, Riqiang Zhan, Tian Yu, Mochen Tang, Yao Liang, Jiajun |
| author_facet | Zou, Minqiang Lv, Zhi Jin, Riqiang Zhan, Tian Yu, Mochen Tang, Yao Liang, Jiajun |
| contents | Multi-view egocentric hand tracking is a challenging task and plays a critical role in VR interaction. In this report, we present a method that uses multi-view input images and camera extrinsic parameters to estimate both hand shape and pose. To reduce overfitting to the camera layout, we apply crop jittering and extrinsic parameter noise augmentation. Additionally, we propose an offline neural smoothing post-processing method to further improve the accuracy of hand position and pose. Our method achieves 13.92mm MPJPE on the Umetrack dataset and 21.66mm MPJPE on the HOT3D dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_19362 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | 1st Place Solution of Multiview Egocentric Hand Tracking Challenge ECCV2024 Zou, Minqiang Lv, Zhi Jin, Riqiang Zhan, Tian Yu, Mochen Tang, Yao Liang, Jiajun Computer Vision and Pattern Recognition Artificial Intelligence Multi-view egocentric hand tracking is a challenging task and plays a critical role in VR interaction. In this report, we present a method that uses multi-view input images and camera extrinsic parameters to estimate both hand shape and pose. To reduce overfitting to the camera layout, we apply crop jittering and extrinsic parameter noise augmentation. Additionally, we propose an offline neural smoothing post-processing method to further improve the accuracy of hand position and pose. Our method achieves 13.92mm MPJPE on the Umetrack dataset and 21.66mm MPJPE on the HOT3D dataset. |
| title | 1st Place Solution of Multiview Egocentric Hand Tracking Challenge ECCV2024 |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2409.19362 |