Steadiface: Real-Time Face-Centric Stabilization on Mobile Phones

TL;DR

Steadiface is a real-time mobile video stabilization technique that stabilizes head motion and background simultaneously using face landmarks and optimization, achieving robustness and efficiency for selfie videos.

Contribution

A novel face-centric stabilization method that combines CNN-based landmark detection with optimization for real-time mobile performance.

Findings

Effective stabilization of head and background in field tests.

Robust to large head poses, occlusion, and camera motions.

Runs efficiently at 8.1 ms/frame on mobile devices.

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).