BriefGPT.xyz
Jan, 2018
Total Capture: 用于追踪人脸、手和身体的3D形变模型
Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies
HTML
PDF
Hanbyul Joo, Tomas Simon, Yaser Sheikh
TL;DR
本文研究了一种捕捉多种尺度的人类运动的统一变形模型，称其为“Frankenstein”模型，并在基础上优化构建出“Adam”模型，使其可以被用于捕捉社交群体的大运动和细微的面部、手势运动。
Abstract
We present a unified
deformation model
for the
markerless capture
of multiple scales of
human movement
, including facial expressions, body
→