Scholarlink

Human skeleton data plays a crucial role in healthcare, rehabilitation, and human-computer interaction. However, traditional motion capture methods are often expensive and highly dependent on controlled environments. To address these limitations, we propose a novel framework based on Diffusion and Transformer models that reconstructs full-body skeleton sequences from foot pressure data collected via smart insoles.

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

Diffusion-TS: A Hybrid Model for Human Skeleton Prediction

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Yuren Zhang,
  • Atsuya Watanabe,
  • Zhongnan Pu,
  • Lei Jing

摘要

Human skeleton data plays a crucial role in healthcare, rehabilitation, and human-computer interaction. However, traditional motion capture methods are often expensive and highly dependent on controlled environments. To address these limitations, we propose a novel framework based on Diffusion and Transformer models that reconstructs full-body skeleton sequences from foot pressure data collected via smart insoles.