Chunjin Song, Zhijie Wu, Bastian Wandt, Leonid Sigal, Helge Rhodin
TL;DR使用双分支网络和体积渲染生成照片级逼真的 3D 人体图像,通过限制频率分量和观察帧一致性,实现了保留高频细节和确保身体轮廓一致性的高保真度人体 3D 模型重建。
Abstract
For reconstructing high-fidelity human 3d models from monocular videos, it is
crucial to maintain consistent large-scale body shapes along with finely
matched subtle wrinkles. This paper explores the observation