Maskfacegan: Masked GAN Latent Code Optimization for High-Resolution Face Editing
International Scientific Journal of Engineering and Management · 02.05.2026 · 05 (05) · 1-9
DOI: 10.55041/isjem06926 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Scientific Journal of Engineering and Management, online erschienen am 02.05.2026. Verfasst von Nimmagadda Chandra Sekhar und 3 weiteren Autor:innen.
Abstract (Originalsprache)
Face editing is a key research area in computer vision, but existing methods often suffer from low-resolution outputs, visual artifacts, and limited control over specific facial attributes, leading to unintended changes. This paper introduces MaskFaceGAN, a novel approach for precise local facial attribute editing. It optimizes the latent code of a pre-trained StyleGAN2 model using multiple constraints to preserve image content, accurately generate desired attributes, and restrict modifications to selected regions. These constraints are guided by a differentiable attribute classifier and face parser. Experimental results on FRGC, SiblingsDB-HQf, and XM2VTS datasets demonstrate that MaskFaceGAN achieves high-quality, high-resolution (1024 × 1024) edits with improved control and reduced attribute entanglement compared to existing methods. Index Terms— Facial attribute editing, generative adversarial networks, GAN inversion, latent code optimization.
Zitieren
APA
Sekhar, N. C., Sagar, A. P., Chandrika, G. L. N., & Ravya,, C. (2026). Maskfacegan: Masked GAN Latent Code Optimization for High-Resolution Face Editing. International Scientific Journal of Engineering and Management, 05(05), 1-9. https://doi.org/10.55041/isjem06926
Vancouver
Sekhar NC, Sagar AP, Chandrika GLN, Ravya, C. Maskfacegan: Masked GAN Latent Code Optimization for High-Resolution Face Editing. International Scientific Journal of Engineering and Management. 2026;05(05):1-9. doi:10.55041/isjem06926
BibTeX
@article{Sekhar2026,
author = {Sekhar, Nimmagadda Chandra and Sagar, Ajmira Prem and Chandrika, Gangineni Lakshmi Naga and Ravya,, Chimata},
title = {Maskfacegan: Masked GAN Latent Code Optimization for High-Resolution Face Editing},
journal = {International Scientific Journal of Engineering and Management},
year = {2026},
volume = {05},
number = {05},
pages = {1--9},
doi = {10.55041/isjem06926}
}
EUVIMED