DAPC-Net: Deformable Alignment and Pyramid Context Completion Networks for Video Inpainting

Video inpainting aims to fill missing regions with plausible content in a video sequence. Deep learning-based video inpainting methods have made promising progress over the past few years. However, these methods tend to generate degraded completion content, such as missing textural details. To addre...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE signal processing letters 2021, Vol.28, p.1145-1149
Hauptverfasser:	Wu, Zhiliang, Zhang, Kang, Xuan, Hanyu, Yang, Jian, Yan, Yan
Format:	Artikel
Sprache:	eng
Schlagworte:	Alignment Coherence Context Convolution Decoding deformable convolution ali- gnment Deformation Formability pyramid-context completion Redundancy Semantics Task analysis Video inpainting Visualization
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!