Abstract
Aiming at the unreliable and over-smoothing problems of the initial motion vector field in existing smoothing methods, a motion vector field smoothing algorithm is proposed. Motion vector outliers can be found in the initial motion vector field by measuring the angle between each motion vector and the average of its neighboring MVs. Based on the location of the outliers, an outlier map is generated. Through evolutionary rules, some hidden outliers are found, and after many iterations, the distribution of motion vector outliers tends to be stable, thus achieving a good balance between over-smoothing and computational redundancy. Spatial-temporal coherence is exploited to correct motion vector outliers. The algorithm significantly improves the visual quality of generated frames and enhances the ability to detect and correct unreliable motion vectors.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
