Multi-Scale Warping for Video Frame Interpolation

A novel video interpolation network to improve the temporal resolutions of video sequences is proposed in this work. We develop a multi-scale warping module to interpolate intermediate frames robustly for both small and large motions. Specifically, the proposed multi-scale warping module deals with...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Whan Choi, Yeong Jun Koh, Chang-Su Kim
Formato: article
Lenguaje:EN
Publicado: IEEE 2021
Materias:
Acceso en línea:https://doaj.org/article/00b115b6a41347b8a4105aa0d1a77cc9
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:00b115b6a41347b8a4105aa0d1a77cc9
record_format dspace
spelling oai:doaj.org-article:00b115b6a41347b8a4105aa0d1a77cc92021-11-18T00:08:26ZMulti-Scale Warping for Video Frame Interpolation2169-353610.1109/ACCESS.2021.3126593https://doaj.org/article/00b115b6a41347b8a4105aa0d1a77cc92021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9606905/https://doaj.org/toc/2169-3536A novel video interpolation network to improve the temporal resolutions of video sequences is proposed in this work. We develop a multi-scale warping module to interpolate intermediate frames robustly for both small and large motions. Specifically, the proposed multi-scale warping module deals with large motions between two consecutive frames using coarse-scale features, while estimating detailed local motions by exploring fine-scale features. To this end, it takes multi-scale features from the encoder and estimates kernel weights and offset vectors for each scale. Finally, it synthesizes multi-scale warping frames and combines them to obtain an intermediate frame. Extensive experimental results demonstrate that the proposed algorithm outperforms state-of-the-art video interpolation algorithms on various benchmark datasets.Whan ChoiYeong Jun KohChang-Su KimIEEEarticleVideo frame interpolationconvolutional neural networkmulti-scale featurekernel-based approachdeformable convolutionadaptive convolutionElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 150470-150479 (2021)
institution DOAJ
collection DOAJ
language EN
topic Video frame interpolation
convolutional neural network
multi-scale feature
kernel-based approach
deformable convolution
adaptive convolution
Electrical engineering. Electronics. Nuclear engineering
TK1-9971
spellingShingle Video frame interpolation
convolutional neural network
multi-scale feature
kernel-based approach
deformable convolution
adaptive convolution
Electrical engineering. Electronics. Nuclear engineering
TK1-9971
Whan Choi
Yeong Jun Koh
Chang-Su Kim
Multi-Scale Warping for Video Frame Interpolation
description A novel video interpolation network to improve the temporal resolutions of video sequences is proposed in this work. We develop a multi-scale warping module to interpolate intermediate frames robustly for both small and large motions. Specifically, the proposed multi-scale warping module deals with large motions between two consecutive frames using coarse-scale features, while estimating detailed local motions by exploring fine-scale features. To this end, it takes multi-scale features from the encoder and estimates kernel weights and offset vectors for each scale. Finally, it synthesizes multi-scale warping frames and combines them to obtain an intermediate frame. Extensive experimental results demonstrate that the proposed algorithm outperforms state-of-the-art video interpolation algorithms on various benchmark datasets.
format article
author Whan Choi
Yeong Jun Koh
Chang-Su Kim
author_facet Whan Choi
Yeong Jun Koh
Chang-Su Kim
author_sort Whan Choi
title Multi-Scale Warping for Video Frame Interpolation
title_short Multi-Scale Warping for Video Frame Interpolation
title_full Multi-Scale Warping for Video Frame Interpolation
title_fullStr Multi-Scale Warping for Video Frame Interpolation
title_full_unstemmed Multi-Scale Warping for Video Frame Interpolation
title_sort multi-scale warping for video frame interpolation
publisher IEEE
publishDate 2021
url https://doaj.org/article/00b115b6a41347b8a4105aa0d1a77cc9
work_keys_str_mv AT whanchoi multiscalewarpingforvideoframeinterpolation
AT yeongjunkoh multiscalewarpingforvideoframeinterpolation
AT changsukim multiscalewarpingforvideoframeinterpolation
_version_ 1718425202972426240