2021/08/15 by Junheum Park, Park, Junheum, Chul Lee +4 · 10 citations
Computer Science · Engineering · #Advanced Image Processing Techniques #Advanced Vision and Imaging #Algorithm #Artificial intelligence #Block-matching algorithm #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #FOS: Computer and information sciences #Frame (networking) #Image Processing Techniques and Applications #Interpolation (computer graphics) #Motion (physics) #Motion estimation #Motion interpolation #Reference frame #Residual #Residual frame #Set (abstract data type) #Telecommunications #Video processing #Video tracking #cs.CV
paper · pdf · doi:10.48550/arxiv.2108.06815
published in arXiv (Cornell University) (Cornell University) · Accepted to ICCV2021
arxiv created 2021/08/15 · openalex publication_date 2021/08/15 · arxiv updated 2021/08/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
We propose a novel video frame interpolation algorithm based on asymmetric bilateral motion estimation (ABME), which synthesizes an intermediate frame between two input frames. First, we predict symmetric bilateral motion fields to interpolate an anchor frame. Second, we estimate asymmetric bilateral motions fields from the anchor frame to the input frames. Third, we use the asymmetric fields to warp the input frames backward and reconstruct the intermediate frame. Last, to refine the intermediate frame, we develop a new synthesis network that generates a set of dynamic filters and a residual frame using local and global information. Experimental results show that the proposed algorithm achieves excellent performance on various datasets. The source codes and pretrained models are available at https://github.com/JunHeum/ABME.