Parameter efficient face frontalization in image sequences via GAN inversion
IET Image Processing · 2025-01 · 19 (1)
DOI: 10.1049/ipr2.70003 ↗Kurz gefasst
Fachartikel in der Zeitschrift IET Image Processing, online erschienen am 05.02.2025. Verfasst von Mohammadhossein Ahmadi und 2 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Processing facial images with varying poses is a significant challenge. Most existing face frontalization methods rely on heavy architectures that struggle with small datasets and produce low‐quality images. Additionally, although video frames provide richer information, these methods typically use single images due to the lack of suitable multi‐image datasets. To address these issues, a parameter‐efficient framework for high‐quality face frontalization in both single and multi‐frame scenarios is proposed. First, a high‐quality, diverse dataset is created for single and multi‐image face frontalization tasks. Second, a novel single‐image face frontalization method is introduced by combining GAN inversion with transfer learning. This approach reduces the number of trainable parameters by over 91% compared to existing GAN inversion methods while achieving far more photorealistic results than GAN‐based methods. Finally, this method is extended to sequences of images, using attention mechanisms to merge information from multiple frames. This multi‐frame approach reduces artefacts like eye blinks and improves reconstruction quality. Experiments demonstrate that this single‐image method outperforms pSp, a state‐of‐the‐art GAN inversion method, with a 0.15 LPIPS improvement and a 0.10 increase in ID similarity. This multi‐frame approach further improves identity preservation to 0.87, showcasing its effectiveness for high‐quality frontal‐view reconstructions.
Zitieren
APA
Ahmadi, M., Kambarani, N., & Mohammadi, M. R. (2025). Parameter efficient face frontalization in image sequences via GAN inversion. IET Image Processing, 19(1). https://doi.org/10.1049/ipr2.70003
Vancouver
Ahmadi M, Kambarani N, Mohammadi MR. Parameter efficient face frontalization in image sequences via GAN inversion. IET Image Processing. 2025;19(1). doi:10.1049/ipr2.70003
BibTeX
@article{Ahmadi2025,
author = {Ahmadi, Mohammadhossein and Kambarani, Nima and Mohammadi, Mohammad Reza},
title = {Parameter efficient face frontalization in image sequences via GAN inversion},
journal = {IET Image Processing},
year = {2025},
volume = {19},
number = {1},
doi = {10.1049/ipr2.70003}
}
EUVIMED