CVPR2020

HUMBI: A Large Multiview Dataset of Human Body Expressions

Zhixuan Yu, Jae Shin Yoon, In Kyu Lee, Prashanth Venkatesh, Jaesik Park, Jihun Yu, Hyun Soo Park

Abstract

We present a new large dataset of multiview human body expressions for modeling view-specific appearance and geometry. 107 synchronized cameras capture the expressions of 772 distinctive subjects. We focus on five elementary expressions: face (blue), gaze (yellow), hand (pink and purple), body (light orange), and garment including top (light blue) and bottom (light green).