Asymmetric Bilateral Motion Estimation for Video Frame Interpolation
This work addresses the problem of generating high-quality intermediate frames in videos, which is incremental as it builds on existing motion estimation methods.
The authors tackled video frame interpolation by proposing an asymmetric bilateral motion estimation algorithm that predicts motion fields and refines the intermediate frame with a synthesis network, achieving excellent performance on various datasets.
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.