From Autoencoders to CycleGAN: Robust Unpaired Face Manipulation via Adversarial Learning

• URL: http://arxiv.org/abs/2509.12176v1
• Date: Mon, 15 Sep 2025 17:40:19 GMT
• Title: From Autoencoders to CycleGAN: Robust Unpaired Face Manipulation via Adversarial Learning
• Authors: Collin Guo,
• Abstract summary: We study unpaired face manipulation via adversarial learning, moving from autoencoder baselines to a robust, guided CycleGAN framework.<n>Our approach integrates spectral normalization for stable training, identity- and perceptual-guided losses to preserve subject identity and high-level structure.<n>Experiments show that our adversarial trained CycleGAN improves realism (FID), perceptual quality (LPIPS), and identity preservation (ID-Sim) over autoencoders.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• A Dual-Branch CNN for Robust Detection of AI-Generated Facial Forgeries [4.313893060699182]
  Face forgery techniques pose significant threats to AI security, digital media integrity, and public trust.<n>We propose a novel dual-branch convolutional neural network for face forgery detection.<n>We evaluate our model on the DiFF benchmark, which includes forged images generated from four representative methods.
  arXiv  Detail & Related papers  (2025-10-28T17:06:40Z)
• From Large Angles to Consistent Faces: Identity-Preserving Video Generation via Mixture of Facial Experts [69.44297222099175]
  We introduce a Mixture of Facial Experts (MoFE) that captures distinct but mutually reinforcing aspects of facial attributes.<n>To mitigate dataset limitations, we have tailored a data processing pipeline centered on two key aspects: Face Constraints and Identity Consistency.<n>We have curated and refined a Large Face Angles (LFA) dataset from existing open-source human video datasets.
  arXiv  Detail & Related papers  (2025-08-13T04:10:16Z)
• Show and Polish: Reference-Guided Identity Preservation in Face Video Restoration [9.481604837168762]
  Face Video Restoration (FVR) aims to recover high-quality face videos from degraded versions.<n>Traditional methods struggle to preserve fine-grained, identity-specific features when degradation is severe.<n>We introduce IP-FVR, a novel method that leverages a high-quality reference face image as a visual prompt to provide identity conditioning during the denoising process.
  arXiv  Detail & Related papers  (2025-07-14T14:01:37Z)
• A Deep Learning Approach for Facial Attribute Manipulation and Reconstruction in Surveillance and Reconnaissance [5.980822697955566]
  Surveillance systems play a critical role in security and reconnaissance, but their performance is often compromised by low-quality images and videos.<n>Existing AI-based facial analysis models suffer from biases related to skin tone variations and partially occluded faces.<n>We propose a data-driven platform that enhances surveillance capabilities by generating synthetic training data tailored to compensate for dataset biases.
  arXiv  Detail & Related papers  (2025-06-06T23:09:17Z)
• Towards Generating Realistic Underwater Images [0.0]
  We investigate the performance of image translation models for generating realistic underwater images using the VAROS dataset.<n>For paired image translation, pix2pix achieves the best FID scores due to its paired supervision and PatchGAN discriminator.<n>For unpaired methods, CycleGAN achieves a competitive FID score by leveraging cycle-consistency loss, whereas CUT, which replaces cycle-consistency with contrastive learning, attains higher SSIM.
  arXiv  Detail & Related papers  (2025-05-20T12:44:19Z)
• G2Face: High-Fidelity Reversible Face Anonymization via Generative and Geometric Priors [71.69161292330504]
  Reversible face anonymization seeks to replace sensitive identity information in facial images with synthesized alternatives. This paper introduces Gtextsuperscript2Face, which leverages both generative and geometric priors to enhance identity manipulation. Our method outperforms existing state-of-the-art techniques in face anonymization and recovery, while preserving high data utility.
  arXiv  Detail & Related papers  (2024-08-18T12:36:47Z)
• Alleviating Catastrophic Forgetting in Facial Expression Recognition with Emotion-Centered Models [49.3179290313959]
  The proposed method, emotion-centered generative replay (ECgr), tackles this challenge by integrating synthetic images from generative adversarial networks. ECgr incorporates a quality assurance algorithm to ensure the fidelity of generated images. The experimental results on four diverse facial expression datasets demonstrate that incorporating images generated by our pseudo-rehearsal method enhances training on the targeted dataset and the source dataset.
  arXiv  Detail & Related papers  (2024-04-18T15:28:34Z)
• Joint fMRI Decoding and Encoding with Latent Embedding Alignment [77.66508125297754]
  We introduce a unified framework that addresses both fMRI decoding and encoding. Our model concurrently recovers visual stimuli from fMRI signals and predicts brain activity from images within a unified framework.
  arXiv  Detail & Related papers  (2023-03-26T14:14:58Z)
• Attentive Symmetric Autoencoder for Brain MRI Segmentation [56.02577247523737]
  We propose a novel Attentive Symmetric Auto-encoder based on Vision Transformer (ViT) for 3D brain MRI segmentation tasks. In the pre-training stage, the proposed auto-encoder pays more attention to reconstruct the informative patches according to the gradient metrics. Experimental results show that our proposed attentive symmetric auto-encoder outperforms the state-of-the-art self-supervised learning methods and medical image segmentation models.
  arXiv  Detail & Related papers  (2022-09-19T09:43:19Z)
• A Shared Representation for Photorealistic Driving Simulators [83.5985178314263]
  We propose to improve the quality of generated images by rethinking the discriminator architecture. The focus is on the class of problems where images are generated given semantic inputs, such as scene segmentation maps or human body poses. We aim to learn a shared latent representation that encodes enough information to jointly do semantic segmentation, content reconstruction, along with a coarse-to-fine grained adversarial reasoning.
  arXiv  Detail & Related papers  (2021-12-09T18:59:21Z)
• Identity-Aware CycleGAN for Face Photo-Sketch Synthesis and Recognition [61.87842307164351]
  We first propose an Identity-Aware CycleGAN (IACycleGAN) model that applies a new perceptual loss to supervise the image generation network. It improves CycleGAN on photo-sketch synthesis by paying more attention to the synthesis of key facial regions, such as eyes and nose. We develop a mutual optimization procedure between the synthesis model and the recognition model, which iteratively synthesizes better images by IACycleGAN.
  arXiv  Detail & Related papers  (2021-03-30T01:30:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.