Scholarlink

<p>We present an animatable 3D Gaussian representation for synthesizing high-fidelity human videos under novel views and poses in real time. Given multi-view videos of a human subject, we learn a collection of 3D Gaussians in the canonical space of the rest pose. Each Gaussian is associated with a few basic properties (i.e., position, opacity, scale, rotation, spherical harmonics coefficients) representing the average human appearance across all video frames, as well as a latent code and a set of blend weights for dynamic appearance correction and pose transformation. The latent code is fed to an Multi-layer Perceptron (MLP) with a target pose to correct Gaussians in the canonical space to capture appearance changes under the target pose. The corrected Gaussians are then transformed to the target pose using linear blend skinning (LBS) with their blend weights. High-fidelity human images under novel views and poses can be rendered in real time through Gaussian splatting. Compared to state-of-the-art NeRF-based methods, our animatable Gaussian representation produces more compelling results with well captured details, and achieves superior rendering performance.</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

Animatable 3D Gaussians for modeling dynamic humans

  • 期刊论文

  • 发表日期：

    2025年1月22日

查看全文
  • Yukun Xu,
  • Keyang Ye,
  • Tianjia Shao,
  • Yanlin Weng

摘要

We present an animatable 3D Gaussian representation for synthesizing high-fidelity human videos under novel views and poses in real time. Given multi-view videos of a human subject, we learn a collection of 3D Gaussians in the canonical space of the rest pose. Each Gaussian is associated with a few basic properties (i.e., position, opacity, scale, rotation, spherical harmonics coefficients) representing the average human appearance across all video frames, as well as a latent code and a set of blend weights for dynamic appearance correction and pose transformation. The latent code is fed to an Multi-layer Perceptron (MLP) with a target pose to correct Gaussians in the canonical space to capture appearance changes under the target pose. The corrected Gaussians are then transformed to the target pose using linear blend skinning (LBS) with their blend weights. High-fidelity human images under novel views and poses can be rendered in real time through Gaussian splatting. Compared to state-of-the-art NeRF-based methods, our animatable Gaussian representation produces more compelling results with well captured details, and achieves superior rendering performance.