Scholarlink

<p>Hand mesh reconstruction technologies play an important role in computer vision, as they facilitate many applications including virtual/augmented reality, human-computer interaction, etc. However, current methods typically rely on computationally intensive architectures with excessive parameters and storage demands to achieve accuracy. In this paper, we propose a lightweight network via Spiral GCN balancing accuracy and efficiency, named LiteSpiralGCN. Our approach includes an Attention Sampling (AS) module to enhance keypoint feature interactions, a SpiralGCN module for efficient and flexible decoding, and a refinement method that leverages multi-scale and multi-stage information to boost reconstruction accuracy. Experiments conducted on benchmark datasets demonstrate that LiteSpiralGCN effectively balances parameter scale and reconstruction accuracy. Specifically, on the FreiHAND dataset, LiteSpiralGCN achieves a PA-MPJPE of 6.5 mm and a PA-MPVPE of 6.6 mm using only 9.77M parameters. Our code is publicly available at: <a href="https://github.com/minqili/LiteSpiralGCN">https://github.com/minqili/LiteSpiralGCN</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

LiteSpiralGCN: Lightweight 3D hand mesh reconstruction via spiral graph convolution

  • 期刊论文

  • 发表日期：

    2025年4月29日

查看全文
  • Yiteng Wang,
  • Minqi Li,
  • Kaibing Zhang,
  • Xiangjian He

摘要

Hand mesh reconstruction technologies play an important role in computer vision, as they facilitate many applications including virtual/augmented reality, human-computer interaction, etc. However, current methods typically rely on computationally intensive architectures with excessive parameters and storage demands to achieve accuracy. In this paper, we propose a lightweight network via Spiral GCN balancing accuracy and efficiency, named LiteSpiralGCN. Our approach includes an Attention Sampling (AS) module to enhance keypoint feature interactions, a SpiralGCN module for efficient and flexible decoding, and a refinement method that leverages multi-scale and multi-stage information to boost reconstruction accuracy. Experiments conducted on benchmark datasets demonstrate that LiteSpiralGCN effectively balances parameter scale and reconstruction accuracy. Specifically, on the FreiHAND dataset, LiteSpiralGCN achieves a PA-MPJPE of 6.5 mm and a PA-MPVPE of 6.6 mm using only 9.77M parameters. Our code is publicly available at: https://github.com/minqili/LiteSpiralGCN.