GatedUniPose: A Novel Approach for Pose Estimation Combining UniRepLKNet and Gated Convolution
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912024398659584 |
|---|---|
| author | Feng, Liang Xu, Ming Wen, Lihua Shen, Zhixuan |
| author_facet | Feng, Liang Xu, Ming Wen, Lihua Shen, Zhixuan |
| contents | Pose estimation is a crucial task in computer vision, with wide applications in autonomous driving, human motion capture, and virtual reality. However, existing methods still face challenges in achieving high accuracy, particularly in complex scenes. This paper proposes a novel pose estimation method, GatedUniPose, which combines UniRepLKNet and Gated Convolution and introduces the GLACE module for embedding. Additionally, we enhance the feature map concatenation method in the head layer by using DySample upsampling. Compared to existing methods, GatedUniPose excels in handling complex scenes and occlusion challenges. Experimental results on the COCO, MPII, and CrowdPose datasets demonstrate that GatedUniPose achieves significant performance improvements with a relatively small number of parameters, yielding better or comparable results to models with similar or larger parameter sizes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_07752 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GatedUniPose: A Novel Approach for Pose Estimation Combining UniRepLKNet and Gated Convolution Feng, Liang Xu, Ming Wen, Lihua Shen, Zhixuan Computer Vision and Pattern Recognition Pose estimation is a crucial task in computer vision, with wide applications in autonomous driving, human motion capture, and virtual reality. However, existing methods still face challenges in achieving high accuracy, particularly in complex scenes. This paper proposes a novel pose estimation method, GatedUniPose, which combines UniRepLKNet and Gated Convolution and introduces the GLACE module for embedding. Additionally, we enhance the feature map concatenation method in the head layer by using DySample upsampling. Compared to existing methods, GatedUniPose excels in handling complex scenes and occlusion challenges. Experimental results on the COCO, MPII, and CrowdPose datasets demonstrate that GatedUniPose achieves significant performance improvements with a relatively small number of parameters, yielding better or comparable results to models with similar or larger parameter sizes. |
| title | GatedUniPose: A Novel Approach for Pose Estimation Combining UniRepLKNet and Gated Convolution |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.07752 |