TL;DRELICIT 是一种基于 3D 几何和视觉语义先验的模型,借助于 CLIP 模型以及基于分割的采样策略,可以从单张图片中生成逼真的、可动画的 3D 人体模型。
Abstract
Existing neural rendering methods for creating human avatars typically either
require dense input signals such as video or multi-view images, or leverage a
learned prior from large-scale specific 3D human dataset