Original Summary

Hi all, as part of my PhD, I released the world’s largest public dataset of synthetic faces &quot;Cafca&quot;.<p>I used it to train a foundation model for 3D face reconstruction and novel view synthesis. It is also meant to serve as a prior for animatable avatars, semantic segmentation, and relighting. Here is what it contains:<p># Images: 1.755 M (512x512) # Identities: 1,500 # Expressions: 13 # Environments: 3 # Views: 30<p>The dataset comes with GT cameras and pseudo-GT keypoints and 3D meshes (FLAME, via VHAP) and is released under a CC BY-NC-SA 4.0 license.<p>The easiest way to get started is Hugging Face (see link on dataset page).<p>Hope you find it useful!

  • 情报分类：综合情报
  • 分类依据：内容未命中明确的垂直分类规则，归入综合情报
  • 信息来源：Hacker News 新项目
  • 发布时间：2026/9/28 18:56:52