Please reload

IMNet for High Resolution Video Frame Interpolation

Tomer Peleg, Pablo Szekely, Doron Sabo and Omry Sendik

Samsung Israel R&D Center


Video frame interpolation is a long-studied problem in the video processing field. Recently, deep learning approaches have been applied to this problem, showing impressive results on low-resolution benchmarks. However, these methods do not scale-up favorably to high resolutions.
Specifically, when the motion exceeds a typical number of pixels, their interpolation quality is degraded. Moreover, their run time renders them impractical for real-time applications.
In this paper we propose IM-Net: an interpolated motion neural network. We used an economic structured architecture and end-to-end training with multi-scale tailored losses.
In particular, we formulate interpolated motion estimation as classification rather than regression. IM-Net outperforms previous methods by more than 1.3dB (PSNR) on a high resolution version of the recently introduced Vimeo triplet dataset. Moreover, the network runs in less than 33msec on a single GPU for HD resolution.


Please reload


author = {Peleg, Tomer and Szekely, Pablo and Sabo, Doron and Sendik, Omry},
title = {IM-Net for High Resolution Video Frame Interpolation},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}}