A Domain-Guided Noise-Optimization-Based Inversion Method for Facial Image Manipulation
Document Type
Article
Publication Date
1-1-2021
Abstract
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 novel domain-guided encoder called Image2latent to project the image to StyleGAN2 latent space, which can reconstruct an input image with high-quality and maintain its semantic meaning well; 2) a noise optimization mechanism in which a set of noise vectors are used to capture the high-frequency details such as image edges, further improving image reconstruction quality; and 3) a mask for seamless image fusion and local style migration. We further propose a novel semantic alignment evaluation pipeline. It evaluates the semantic alignment with an inverse code by using different attribute boundaries. Extensive qualitative and quantitative comparisons show that DNI can capture rich semantic information and achieve a satisfactory image reconstruction. It can realize a variety of facial image manipulation tasks and outperform state of the art.
Identifier
85112101743 (Scopus)
Publication Title
IEEE Transactions on Image Processing
External Full Text Location
https://doi.org/10.1109/TIP.2021.3089905
e-ISSN
19410042
ISSN
10577149
PubMed ID
34156940
First Page
6198
Last Page
6211
Volume
30
Grant
61773367
Fund Ref
National Natural Science Foundation of China
Recommended Citation
Yang, Nan; Zheng, Zeyu; Zhou, Mengchu; Guo, Xiwang; Qi, Liang; and Wang, Tianran, "A Domain-Guided Noise-Optimization-Based Inversion Method for Facial Image Manipulation" (2021). Faculty Publications. 4708.
https://digitalcommons.njit.edu/fac_pubs/4708