用新模块提升复杂场景下人体姿态估计精度
GatedUniPose: A Novel Approach for Pose Estimation Combining UniRepLKNet and Gated Convolution
- 融合UniRepLKNet与门控卷积，引入GLACE嵌入模块
- 在COCO等数据集上参数少却性能领先
- 适合对精度和效率有要求的实时应用
人体姿态估计是计算机视觉中的关键任务，广泛应用于自动驾驶、动作捕捉和虚拟现实。现有方法在复杂场景下仍面临精度挑战。本文提出GatedUniPose，结合UniRepLKNet与门控卷积，并引入GLACE嵌入模块；同时在头部层改进特征图拼接方式，采用DySample上采样。在COCO、MPII和CrowdPose数据集上的实验表明，GatedUniPose在参数量较少的情况下实现显著性能提升，表现优于或媲美参数量相当甚至更大的模型。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。