Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Guo, Collin, Qian, Yi
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2509.12176
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912799194611712
author Guo, Collin
Qian, Yi
author_facet Guo, Collin
Qian, Yi
contents Human face synthesis and manipulation are increasingly important in entertainment and AI, with a growing demand for highly realistic, identity-preserving images even when only unpaired, unaligned datasets are available. We study unpaired face manipulation via adversarial learning, moving from autoencoder baselines to a robust, guided CycleGAN framework. While autoencoders capture coarse identity, they often miss fine details. Our approach integrates spectral normalization for stable training, identity- and perceptual-guided losses to preserve subject identity and high-level structure, and landmark-weighted cycle constraints to maintain facial geometry across pose and illumination changes. Experiments show that our adversarial trained CycleGAN improves realism (FID), perceptual quality (LPIPS), and identity preservation (ID-Sim) over autoencoders, with competitive cycle-reconstruction SSIM and practical inference times, which achieved high quality without paired datasets and approaching pix2pix on curated paired subsets. These results demonstrate that guided, spectrally normalized CycleGANs provide a practical path from autoencoders to robust unpaired face manipulation.
format Preprint
id arxiv_https___arxiv_org_abs_2509_12176
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From Autoencoders to CycleGAN: Robust Unpaired Face Manipulation via Adversarial Learning
Guo, Collin
Qian, Yi
Machine Learning
Human face synthesis and manipulation are increasingly important in entertainment and AI, with a growing demand for highly realistic, identity-preserving images even when only unpaired, unaligned datasets are available. We study unpaired face manipulation via adversarial learning, moving from autoencoder baselines to a robust, guided CycleGAN framework. While autoencoders capture coarse identity, they often miss fine details. Our approach integrates spectral normalization for stable training, identity- and perceptual-guided losses to preserve subject identity and high-level structure, and landmark-weighted cycle constraints to maintain facial geometry across pose and illumination changes. Experiments show that our adversarial trained CycleGAN improves realism (FID), perceptual quality (LPIPS), and identity preservation (ID-Sim) over autoencoders, with competitive cycle-reconstruction SSIM and practical inference times, which achieved high quality without paired datasets and approaching pix2pix on curated paired subsets. These results demonstrate that guided, spectrally normalized CycleGANs provide a practical path from autoencoders to robust unpaired face manipulation.
title From Autoencoders to CycleGAN: Robust Unpaired Face Manipulation via Adversarial Learning
topic Machine Learning
url https://arxiv.org/abs/2509.12176