Steadiface: Real-Time Face-Centric Stabilization on Mobile Phones
This work addresses video stabilization for selfie videos on mobile devices, representing an incremental improvement over existing methods.
The authors tackled the problem of real-time face-centric video stabilization on mobile phones, achieving a processing speed of 8.1 ms per frame while stabilizing both head motion and background against hand shake and large head poses.
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).