Context-based video frame interpolation via depthwise over-parameterized convolution

被引：0

作者：

Zhang, Haoran ^{[1
,2
]}

Yang, Xiaohui ^{[1
,2
]}

Feng, Zhiquan ^{[1
,2
]}

机构：

[1] Univ Jinan, Shandong Prov Key Lab Network Based Intelligent C, Jinan, Peoples R China

[2] Univ Jinan, Sch Informat Sci & Engn, Jinan, Peoples R China

来源：

JOURNAL OF ELECTRONIC IMAGING | 2021年 / 30卷 / 06期

基金：

中国国家自然科学基金;

关键词：

context information; deep learning; depthwise over-parameterized convolution; frame interpolation; frame-rate up-conversion;

D O I：

10.1117/1.JEI.30.6.063004

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Video frame interpolation is used to generate intermediate frames by estimating the movement of pixels between the input frames. However, problems of blurring, object occlusion, and sudden brightness changes occur in naturally obtained video frames. We propose a context-based video frame interpolation method via depthwise over-parameterized convolution. First, the proposed network obtains the context graphs of the input frames. Subsequently, an adaptive collaboration of flows is adopted to warp the input frames and the context graphs. Then, the frame synthesis network is used to fuse the warped input frames and context graphs to obtain a preliminary estimate of the interpolated frame. Finally, a post-processing module is employed to refine the result. Experimental results on several datasets demonstrate that the proposed method performs qualitatively and quantitatively better than state-of-the-art methods. (C) 2021 SPIE and IS&T

引用

页数：17