Image Inpainting by End-to-End Cascaded Refinement with Mask Awareness

Inpainting arbitrary missing regions is challenging because learning valid features for various masked regions is nontrivial. Though U-shaped encoder-decoder frameworks have been witnessed to be successful, most of them share a common drawback of mask unawareness in feature extraction because all co...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on image processing 2021-01, Vol.PP, p.1-1
Hauptverfasser:	Zhu, Manyu, He, Dongliang, Li, Xin, Lia, Chao, Lib, Fu, Liu, Xiao, Ding, Errui, Zhang, Zhaoxiang
Format:	Artikel
Sprache:	eng
Schlagworte:	Cascaded Refinement Coders Convolution Decoding Dynamic Filtering Encoders-Decoders Feature extraction Image Inpainting Image reconstruction Kernel Mask Awareness Scaling factors Shape Task analysis
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!