HUMBI: A Large Multiview Dataset of Human Body Expressions [conference paper]

Conference

IEEE/CVF Conference on Computer Vision and Pattern Recognition - June 14-19, 2020

Authors

Zhixuan Yu (Ph.D. student), Jae Shin Yoon (Ph.D. student), In Kyu Lee, Prashanth Venkatesh (M.S. student), Jaesik Park, Jihun Yu, Hyun Soo Park (assistant professor)

Abstract

This paper presents a new large multiview dataset called HUMBI for human body expressions with natural clothing. The goal of HUMBI is to facilitate modeling view-specific appearance and geometry of gaze, face, hand, body, and garment from assorted people. 107 synchronized HD cam-eras are used to capture 772 distinctive subjects across gen-der, ethnicity, age, and physical condition. With the mul-tiview image streams, we reconstruct high fidelity body ex-pressions using 3D mesh models, which allows representing view-specific appearance using their canonical atlas. We demonstrate that HUMBI is highly effective in learning and reconstructing a complete human model and is complemen-tary to the existing datasets of human body expressions with limited views and subjects such as MPII-Gaze, Multi-PIE, Human3. 6M, and Panoptic Studio datasets.

Link to full paper

HUMBI: A Large Multiview Dataset of Human Body Expressions

Keywords

computer vision