BriefGPT.xyz
Dec, 2022
具有模型先验的一次性隐式可动画化人形头像
One-shot Implicit Animatable Avatars with Model-based Priors
HTML
PDF
Yangyi Huang, Hongwei Yi, Weiyang Liu, Haofan Wang, Boxi Wu...
TL;DR
ELICIT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
→