BriefGPT.xyz
Apr, 2023
PoseVocab: 为人体形象建模学习联合结构的姿态嵌入
PoseVocab: Learning Joint-structured Pose Embeddings for Human Avatar Modeling
HTML
PDF
Zhe Li, Zerong Zheng, Yuxiao Liu, Boyao Zhou, Yebin Liu
TL;DR
提出了一种名为PoseVocab的编码技术,该技术基于训练动态的多视角RGB视频,构建关键姿势和潜在嵌入,以有效地编码动态人体外观细节,从而使得在新的姿势下实现逼真且广泛的动画成为可能。
Abstract
Creating
pose-driven human avatars
is about modeling the mapping from the low-frequency driving pose to high-frequency dynamic human appearances, so an effective
pose encoding method
that can encode high-fidelity
→