Real-Time 3D Face Alignment Using an Encoder-Decoder Network With an Efficient Deconvolution Layer

In the field of 3D face alignment, most researchers have focused on improving the prediction accuracy of algorithms and ignored the portability for practical applications. To this end, this study presents a real-time 3D face-alignment method that uses an encoder-decoder network with an efficient dec...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE signal processing letters Jg. 27; S. 1944 - 1948
Hauptverfasser: Ning, Xin, Duan, Pengfei, Li, Weijun, Zhang, Shaolin
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York IEEE 2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
3D face alignment
Algorithms
Alignment
Coders
Decoding
Deconvolution
encoder decoder network
Encoders-Decoders
Encoding
Face recognition
Faces
Real time
real time application
Real-time systems
Three-dimensional displays
ISSN:1070-9908, 1558-2361
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In the field of 3D face alignment, most researchers have focused on improving the prediction accuracy of algorithms and ignored the portability for practical applications. To this end, this study presents a real-time 3D face-alignment method that uses an encoder-decoder network with an efficient deconvolution layer. The fusion of the encoding and decoding feature adds more abundant features to this network. An efficient deconvolution layer at the decoding stage applies the L1 norm to select useful features and generate abundant ones through linear operations. Experimental results using the standard AFLW2000-3D and AFLW-LFPA datasets show that our algorithm has low prediction errors with real-time applicability.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1070-9908
1558-2361
DOI:10.1109/LSP.2020.3032277