A Domain-Guided Noise-Optimization-Based Inversion Method for Facial Image Manipulation

A style-based architecture (StyleGAN2) yields outstanding results in data-driven unconditional generative image modeling. This work proposes a Domain-guided Noise-optimization-based Inversion (DNI) method to perform facial image manipulation. It works based on an inverse code that includes: 1) a nov...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on image processing Jg. 30; S. 6198 - 6211
Hauptverfasser:	Yang, Nan, Zheng, Zeyu, Zhou, Mengchu, Guo, Xiwang, Qi, Liang, Wang, Tianran
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	New York IEEE 2021 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Aerospace electronics Alignment Coders Computer vision Deep learning domain-guided encoder Domains Generative adversarial networks Generators Image manipulation Image processing Image quality Image reconstruction Noise noise optimization Optimization Semantics Training
ISSN:	1057-7149, 1941-0042, 1941-0042
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!