论文标题
用粗到1的3D CNN增强基于可变形的卷积框架插值
Enhancing Deformable Convolution based Video Frame Interpolation with Coarse-to-fine 3D CNN
论文作者
论文摘要
本文提出了一种新的基于可变形的视频框架插值（VFI）方法，使用粗到细的3D CNN来增强多流量预测。该模型首先使用3D CNN在多个尺度上提取时空特征，并以粗到1的方式估算使用这些特征的多流量。然后使用估计的多流量来扭曲原始输入帧以及上下文图，并且扭曲的结果由合成网络融合以产生最终输出。该VFI方法已针对三个常用的测试数据库的12种最先进的VFI方法进行了充分评估。结果显然表明了所提出的方法的有效性，该方法具有优于其他最先进算法的互插性能，PSNR的增长率高达0.19dB。
This paper presents a new deformable convolution-based video frame interpolation (VFI) method, using a coarse to fine 3D CNN to enhance the multi-flow prediction. This model first extracts spatio-temporal features at multiple scales using a 3D CNN, and estimates multi-flows using these features in a coarse-to-fine manner. The estimated multi-flows are then used to warp the original input frames as well as context maps, and the warped results are fused by a synthesis network to produce the final output. This VFI approach has been fully evaluated against 12 state-of-the-art VFI methods on three commonly used test databases. The results evidently show the effectiveness of the proposed method, which offers superior interpolation performance over other state of the art algorithms, with PSNR gains up to 0.19dB.
