Abstract:
We propose a deep learning-based frame rate upconversion algorithm using bilateral motion estimation. We first estimate bilateral motion fields by employing a convolution...Show MoreMetadata
Abstract:
We propose a deep learning-based frame rate upconversion algorithm using bilateral motion estimation. We first estimate bilateral motion fields by employing a convolutional neural network. Also, we approximate intermediate bi-directional motion fields, assuming linear motions between successive frames. Finally, we develop the synthesis network to produce an intermediate frame by merging the warped frames, which are obtained using the two kinds of motion fields. Experimental results demonstrate that the proposed algorithm generates high-quality intermediate frames on challenging sequences with large motions and occlusion, and outperforms state-of-the-art conventional algorithms.
Published in: 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)
Date of Conference: 18-21 November 2019
Date Added to IEEE Xplore: 05 March 2020
ISBN Information: