BriefGPT.xyz
Apr, 2017
从静态图像预测人类动态
Forecasting Human Dynamics from Static Images
HTML
PDF
Yu-Wei Chao, Jimei Yang, Brian Price, Scott Cohen, Jia Deng
TL;DR
研究使用单个RGB图像预测人体动态，提出了3D Pose Forecasting Network(3D-PFNet)，结合2D预测和3D空间，在多样化的数据源下进行了三步训练，展示了在2D姿势预测和3D姿势恢复上有竞争力的性能结果。
Abstract
This paper presents the first study on forecasting
human dynamics
from static images. The problem is to input a single
rgb image
and generate a sequence of upcoming human body poses in 3D. To address the problem,
→