Scholarlink

<p>We study the problem of creating high-fidelity and animatable 3D avatars from only textual descriptions. Existing text-to-avatar methods are either limited to static avatars which cannot be animated or struggle to generate animatable avatars with promising quality and precise pose control. To address these limitations, we propose AvatarStudio, a generative model that yields explicit textured 3D meshes for animatable human avatars. Specifically, AvatarStudio proposes to incorporate articulation modeling into the explicit mesh representation to support high-resolution rendering and avatar animation. To ensure view consistency and pose controllability of the resulting avatars, we introduce a simple-yet-effective 2D diffusion model conditioned on DensePose for Score Distillation Sampling supervision. By effectively leveraging the synergy between the articulated mesh representation and DensePose-conditional diffusion model, AvatarStudio can create high-quality avatars from text ready for animation. Furthermore, it is competent for many applications, <i>e.g.</i>, multimodal avatar animations and style-guided avatar creation. Please refer to our <a href="https://avatarstudio23.github.io/">project page</a> for more results.</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

AvatarStudio: High-Fidelity and Animatable 3D Avatar Creation from Text

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年4月7日

查看全文
  • Xuanmeng Zhang,
  • Jianfeng Zhang,
  • Chenxu Zhang,
  • Jun Hao Liew,
  • Huichao Zhang,
  • Yi Yang,
  • Jiashi Feng

摘要

We study the problem of creating high-fidelity and animatable 3D avatars from only textual descriptions. Existing text-to-avatar methods are either limited to static avatars which cannot be animated or struggle to generate animatable avatars with promising quality and precise pose control. To address these limitations, we propose AvatarStudio, a generative model that yields explicit textured 3D meshes for animatable human avatars. Specifically, AvatarStudio proposes to incorporate articulation modeling into the explicit mesh representation to support high-resolution rendering and avatar animation. To ensure view consistency and pose controllability of the resulting avatars, we introduce a simple-yet-effective 2D diffusion model conditioned on DensePose for Score Distillation Sampling supervision. By effectively leveraging the synergy between the articulated mesh representation and DensePose-conditional diffusion model, AvatarStudio can create high-quality avatars from text ready for animation. Furthermore, it is competent for many applications, e.g., multimodal avatar animations and style-guided avatar creation. Please refer to our project page for more results.