Back to Search
Start Over
Real-Time Selfie Video Stabilization
- Source :
- CVPR
- Publication Year :
- 2020
- Publisher :
- arXiv, 2020.
-
Abstract
- 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 to the rigid moving least squares 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. Our code and selfie video dataset is available at https://github.com/jiy173/selfievideostabilization.
- Subjects :
- FOS: Computer and information sciences
business.industry
Computer science
Computer Vision and Pattern Recognition (cs.CV)
Frame (networking)
Computer Science - Computer Vision and Pattern Recognition
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Grid
Image stabilization
Convolutional code
Computer vision
Artificial intelligence
Image warping
Moving least squares
Selfie
Focus (optics)
business
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- CVPR
- Accession number :
- edsair.doi.dedup.....0910717ef32fdd968179e632ad4d7708
- Full Text :
- https://doi.org/10.48550/arxiv.2009.02007