Scholarlink

<p>Accurately localizing landmarks on 3D faces is critical for various applications, such as expression recognition, facial surgery navigation, and lip shape analysis. Existing landmarks localization methods generally contain complex calculation processes, which may affect the efficiency. To address this problem, we propose a <b>S</b>imple and <b>E</b>fficient <b>M</b>LP-based <b>Net</b>work (SEMNet) for landmarks localization. We first design a lightweight enhanced geometric affine module to adaptively transform point features in local regions, for improving performance and generalization. Then, to fully utilize the rotation information of the face, a rotation constraint auxiliary branch is introduced for assisting in locating landmarks. In addition, to generate more accurate results, we propose a residual graph convolution discriminator to distinguish predicted locations from real face point clouds locations. Experimental results on two public datasets (FRGC v2 and Bosphorus) and a self-made dataset show that our method achieves high accuracy and efficiency compared to state-of-the-art methods.</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

SEMNet: a simple and efficient MLP-based network for 3D Face point clouds landmarks localization

  • 期刊论文

  • 发表日期：

    2025年2月27日

查看全文
  • Mingyang Lei,
  • Hong Song,
  • Tianyu Fu,
  • Deqiang Xiao,
  • Danni Ai,
  • Jingfan Fan,
  • Yifei Yang,
  • Ying Gu,
  • Jian Yang

摘要

Accurately localizing landmarks on 3D faces is critical for various applications, such as expression recognition, facial surgery navigation, and lip shape analysis. Existing landmarks localization methods generally contain complex calculation processes, which may affect the efficiency. To address this problem, we propose a Simple and Efficient MLP-based Network (SEMNet) for landmarks localization. We first design a lightweight enhanced geometric affine module to adaptively transform point features in local regions, for improving performance and generalization. Then, to fully utilize the rotation information of the face, a rotation constraint auxiliary branch is introduced for assisting in locating landmarks. In addition, to generate more accurate results, we propose a residual graph convolution discriminator to distinguish predicted locations from real face point clouds locations. Experimental results on two public datasets (FRGC v2 and Bosphorus) and a self-made dataset show that our method achieves high accuracy and efficiency compared to state-of-the-art methods.