Scholarlink

<p>Human pose estimation, a pivotal task in computer vision, finds applications in diverse fields such as action recognition, human–computer interaction, and healthcare. Despite recent advances leveraging powerful backbone networks, challenges remain in fully exploiting structural priors and spatial dependencies. This paper introduces PyraFusionPose, a novel pose estimation framework featuring a task-specific backbone architecture and an uncertainty-aware regression head. Our approach integrates both fine-grained local details and global contextual information, enhancing accuracy and robustness. Extensive experiments on the COCO benchmark demonstrate a 0.6% improvement in AP over the state-of-the-art model, ViTPose, with superior performance in complex scenarios such as crowded scenes and occlusions. These findings establish a new standard for human pose estimation and underscore the importance of task-specific design and uncertainty modeling. Source code and models are available at <a href="https://github.com/Eucliwood-bsb/PyraFusionPose">https://github.com/Eucliwood-bsb/PyraFusionPose</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Enhancing human pose estimation accuracy with pyramid fusion Vision Transformers

  • 期刊论文

  • 发表日期：

    2026年1月26日

查看全文
  • ShaoBo Bian,
  • Jianzhong Wang,
  • Yu You,
  • Zibo Yu,
  • Yong Sun,
  • WeiChao Wu

摘要

Human pose estimation, a pivotal task in computer vision, finds applications in diverse fields such as action recognition, human–computer interaction, and healthcare. Despite recent advances leveraging powerful backbone networks, challenges remain in fully exploiting structural priors and spatial dependencies. This paper introduces PyraFusionPose, a novel pose estimation framework featuring a task-specific backbone architecture and an uncertainty-aware regression head. Our approach integrates both fine-grained local details and global contextual information, enhancing accuracy and robustness. Extensive experiments on the COCO benchmark demonstrate a 0.6% improvement in AP over the state-of-the-art model, ViTPose, with superior performance in complex scenarios such as crowded scenes and occlusions. These findings establish a new standard for human pose estimation and underscore the importance of task-specific design and uncertainty modeling. Source code and models are available at https://github.com/Eucliwood-bsb/PyraFusionPose.