GatedUniPose: A Novel Approach for Pose Estimation Combining UniRepLKNet and Gated Convolution

TL;DR

GatedUniPose is a new pose estimation method that combines UniRepLKNet and Gated Convolution, introducing the GLACE module and DySample upsampling to improve accuracy in complex scenes and occlusions.

Contribution

It presents GatedUniPose, a novel approach integrating the GLACE module and DySample upsampling, enhancing pose estimation performance in challenging scenarios.

Findings

Outperforms existing methods on COCO, MPII, and CrowdPose datasets.

Achieves high accuracy with fewer parameters.

Handles occlusion and complex scenes effectively.

Abstract

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.