Frame Rate Up-Conversion under Stationary Constraints of Spatio-Temporal Local Motion
Wendan Ma, Fan Li, Wenjing Yu · 2022 IEEE 5th International Conference on Automation, Electronics and Electrical Engineering (AUTEEE) · 2022
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.