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!
Descripción
Sumario: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.