Real-Time Selfie Video Stabilization
This addresses the problem of shaky selfie videos for users, offering real-time stabilization with optional focus control, though it is incremental as it builds on existing stabilization techniques.
The paper tackles real-time selfie video stabilization by proposing a novel method that runs at 26 fps, using a 1D linear convolutional network to infer rigid moving least squares warping, achieving comparable quality to offline methods with orders of magnitude speed improvement.
We propose a novel real-time selfie video stabilization method. Our method is completely automatic and runs at 26 fps. We use a 1D linear convolutional network to directly infer the rigid moving least squares warping which implicitly balances between the global rigidity and local flexibility. Our network structure is specifically designed to stabilize the background and foreground at the same time, while providing optional control of stabilization focus (relative importance of foreground vs. background) to the users. To train our network, we collect a selfie video dataset with 1005 videos, which is significantly larger than previous selfie video datasets. We also propose a grid approximation method to the rigid moving least squares warping that enables the real-time frame warping. Our method is fully automatic and produces visually and quantitatively better results than previous real-time general video stabilization methods. Compared to previous offline selfie video methods, our approach produces comparable quality with a speed improvement of orders of magnitude.