Scholarlink

<p>We propose a generic human avatar modeling framework, GenericAvatar, which leverages mesh-guided Gaussian splatting to achieve personalized, high-fidelity reconstruction of human bodies or heads from monocular videos. Our method consists of two steps. First, the Gaussian initialization module based on explicit triangular meshes embeds Gaussian splats onto the mesh, thereby stably capturing the low frequency motions and surface deformations of human avatars. Second, the Gaussian adjustment module employs a multi-resolution triplane to encode 3D Gaussian splats, followed by a spatial-posture cross-attention module and an MLP module to adjust Gaussian attributes. The second module effectively overcomes the limitations of traditional linear blend skinning (LBS) in modeling complex non-rigid deformations, enabling precise modeling of high-frequency details such as clothing wrinkles and dynamic hair. By fully integrating the geometric priors provided by explicit meshes with implicit Gaussian representations, GenericAvatar demonstrates high-fidelity reconstruction on PeopleSnapshot, ZJU-Mocap, and a monocular head dataset, preserving complex texture details. Experimental results indicate that GenericAvatar outperforms state-of-the-art methods on both human body reconstruction and head reconstruction. The code is made public in <a href="https://genericavatar2025.github.io">https://genericavatar2025.github.io</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

GenericAvatar: generic human modeling from monocular video based on mesh-guided Gaussians

  • 期刊论文

  • 发表日期：

    2025年5月24日

查看全文
  • Sen Peng,
  • Yihang Fu,
  • Runjie Miu,
  • Tianyi Lv,
  • Baorong Yang,
  • Xiao Dong

摘要

We propose a generic human avatar modeling framework, GenericAvatar, which leverages mesh-guided Gaussian splatting to achieve personalized, high-fidelity reconstruction of human bodies or heads from monocular videos. Our method consists of two steps. First, the Gaussian initialization module based on explicit triangular meshes embeds Gaussian splats onto the mesh, thereby stably capturing the low frequency motions and surface deformations of human avatars. Second, the Gaussian adjustment module employs a multi-resolution triplane to encode 3D Gaussian splats, followed by a spatial-posture cross-attention module and an MLP module to adjust Gaussian attributes. The second module effectively overcomes the limitations of traditional linear blend skinning (LBS) in modeling complex non-rigid deformations, enabling precise modeling of high-frequency details such as clothing wrinkles and dynamic hair. By fully integrating the geometric priors provided by explicit meshes with implicit Gaussian representations, GenericAvatar demonstrates high-fidelity reconstruction on PeopleSnapshot, ZJU-Mocap, and a monocular head dataset, preserving complex texture details. Experimental results indicate that GenericAvatar outperforms state-of-the-art methods on both human body reconstruction and head reconstruction. The code is made public in https://genericavatar2025.github.io.