Enhanced Bi-directional Motion Estimation for Video Frame Interpolation
This work addresses the challenge of efficient and accurate video frame interpolation for applications in video processing, though it appears incremental as it builds on existing motion-based methods.
The authors tackled the problem of video frame interpolation by developing a compact model for bidirectional motion estimation, which is 15 times smaller than PWC-Net and handles complex motions more reliably.
We present a novel simple yet effective algorithm for motion-based video frame interpolation. Existing motion-based interpolation methods typically rely on a pre-trained optical flow model or a U-Net based pyramid network for motion estimation, which either suffer from large model size or limited capacity in handling complex and large motion cases. In this work, by carefully integrating intermediateoriented forward-warping, lightweight feature encoder, and correlation volume into a pyramid recurrent framework, we derive a compact model to simultaneously estimate the bidirectional motion between input frames. It is 15 times smaller in size than PWC-Net, yet enables more reliable and flexible handling of challenging motion cases. Based on estimated bi-directional motion, we forward-warp input frames and their context features to intermediate frame, and employ a synthesis network to estimate the intermediate frame from warped representations. Our method achieves excellent performance on a broad range of video frame interpolation benchmarks. Code and trained models are available at \url{https://github.com/srcn-ivl/EBME}.