2022/03/05 by Hanieh Naderi, Naderi, Hanieh, Mohammad Rahmati +1
Computer Science · Engineering · Mathematics · #Advanced Image Processing Techniques #Advanced Vision and Imaging #Algorithm #Artificial Intelligence (cs.AI) #Artificial intelligence #Block-matching algorithm #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #FOS: Computer and information sciences #FOS: Electrical engineering #Frame (networking) #Frame rate #Image and Video Processing (eess.IV) #Inter frame #Interpolation (computer graphics) #Mathematics #Motion (physics) #Motion estimation #Motion interpolation #Multimedia (cs.MM) #Quarter-pixel motion #Reference frame #Video Coding and Compression Technologies #cs.AI #cs.CV #cs.MM #eess.IV #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2203.03621
Frame rate up-conversion, frame interpolation, motion estimation, motion compensation
arxiv created 2022/03/05 · openalex publication_date 2022/03/05 · arxiv updated 2022/03/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/06
In this paper, we propose a novel motion-compensated frame rate up-conversion (MC-FRUC) algorithm. The proposed algorithm creates interpolated frames by first estimating motion vectors using unilateral (jointing forward and backward) and bilateral motion estimation. Then motion vectors are combined based on adaptive threshold, in order to creates high-quality interpolated frames and reduce block artifacts. Since motion-compensated frame interpolation along unilateral motion trajectories yields holes, a new algorithm is introduced to resolve this problem. The experimental results show that the quality of the interpolated frames using the proposed algorithm is much higher than the existing algorithms.