Affiliation:
1. University of Science and Technology of China, China
2. Microsoft Research Asia, China
Abstract
Video frame synthesis, which consists of
interpolation
and
extrapolation
, is an essential video processing technique that can be applied to various scenarios. However, most existing methods cannot handle small objects or large motion well, especially in high-resolution videos such as 4K videos. To eliminate such limitations, we introduce a neighbor correspondence matching (NCM) algorithm for flow-based frame synthesis. Since the current frame is not available in video frame synthesis, NCM is performed in a current-frame-agnostic fashion to establish multi-scale correspondences in the spatial-temporal neighborhoods of each pixel. Based on the powerful motion representation capability of NCM, we propose a heterogeneous coarse-to-fine scheme for intermediate flow estimation. The coarse-scale and fine-scale modules are trained progressively, making NCM computationally efficient and robust to large motions. We further explore the mechanism of NCM and find that neighbor correspondence is powerful, since it provides multiple-hypotheses motion information for synthesis. Based on this analysis, we introduce a multiple-hypotheses estimation process for video frame extrapolation, resulting in a more robust framework, NCM-MH. Experimental results show that NCM and NCM-MH achieve 31.63 and 28.08 dB for interpolation and extrapolation on the most challenging X4K1000FPS benchmark, outperforming all the other state-of-the-art methods that use two reference frames as input.
Publisher
Association for Computing Machinery (ACM)
Subject
Computer Networks and Communications,Hardware and Architecture
Reference44 articles.
1. Depth-Aware Video Frame Interpolation
2. Memc-net: Motion estimation and motion compensation driven neural network for video interpolation and enhancement;Bao Wenbo;IEEE Trans. Pattern Anal. Mach. Intell.,2019
3. Tim Brooks and Jonathan T Barron. 2019. Learning to synthesize motion blur. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 6840–6848.
4. Ho Kei Cheng Yu-Wing Tai and Chi-Keung Tang. 2021. Rethinking space-time networks with improved memory coverage for efficient video object segmentation. Advances in Neural Information Processing Systems 34 (2021) 11781–11794.
5. Channel Attention Is All You Need for Video Frame Interpolation