AdaCoF: Adaptive Collaboration of Flows for Video Frame Interpolation

Hyeongmin Lee, Taeoh Kim, Tae-young Chung, Daehyun Pak, Yuseok Ban, Sangyoun Lee; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 5316-5325

Abstract


Video frame interpolation is one of the most challenging tasks in video processing research. Recently, many studies based on deep learning have been suggested. Most of these methods focus on finding locations with useful information to estimate each output pixel using their own frame warping operations. However, many of them have Degrees of Freedom (DoF) limitations and fail to deal with the complex motions found in real world videos. To solve this problem, we propose a new warping module named Adaptive Collaboration of Flows (AdaCoF). Our method estimates both kernel weights and offset vectors for each target pixel to synthesize the output frame. AdaCoF is one of the most generalized warping modules compared to other approaches, and covers most of them as special cases of it. Therefore, it can deal with a significantly wide domain of complex motions. To further improve our framework and synthesize more realistic outputs, we introduce dual-frame adversarial loss which is applicable only to video frame interpolation tasks. The experimental results show that our method outperforms the state-of-the-art methods for both fixed training set environments and the Middlebury benchmark. Our source code is available at https://github.com/HyeongminLEE/AdaCoF-pytorch

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Lee_2020_CVPR,
author = {Lee, Hyeongmin and Kim, Taeoh and Chung, Tae-young and Pak, Daehyun and Ban, Yuseok and Lee, Sangyoun},
title = {AdaCoF: Adaptive Collaboration of Flows for Video Frame Interpolation},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}