Sorry, you need to enable JavaScript to visit this website.

STEADIFACE: REAL-TIME FACE-CENTRIC STABILIZATION ON MOBILE PHONES

Citation Author(s):
Fuhao Shi, Sung-Fang Tsai, Youyou Wang, Chia-Kai Liang
Submitted by:
Fuhao Shi
Last updated:
24 September 2019 - 4:05am
Document Type:
Poster
Document Year:
2019
Event:
Presenters:
Sung-Fang Tsai
Paper Code:
1025

Abstract

We present Steadiface, a new real-time face-centric video stabilization method that simultaneously removes hand shake and keeps subject's head stable. We use a CNN to estimate the face landmarks and use them to optimize a stabilized head center. We then formulate an optimization problem to find a virtual camera pose that locates the face to the stabilized head center while retains smooth rotation and translation transitions across frames. We test the proposed method on fieldtest videos and show it stabilizes both the head motion and background. It is robust to large head pose, occlusion, facial appearance variations, and different kinds of camera motions. We show our method advances the state of art in selfie video stabilization by comparing against alternative methods. The whole process runs very efficiently on a modern mobile phone (8.1 ms/frame).

up
0 users have voted:

Files

steadiface_poster.pdf

(219)