MyTimeMachine: Personalized Facial Age Transformation

2024-11-21

arXiv.org

AI Summary

To address the challenge of modeling individualized aging variations under limited global prior knowledge in personalized facial age transformation, this paper proposes a lightweight, data-efficient method requiring only 50 subject-specific cross-age images. Built upon the StyleGAN2 architecture, we introduce a learnable Adapter network that jointly integrates global aging priors with subject-specific features. Our approach enforces three complementary constraints: a personalized aging loss, extrapolation regularization, and adaptive w-norm regularization, while explicitly modeling temporal consistency for video sequences. Experimental results demonstrate that the method achieves high-fidelity age synthesis with minimal training data, significantly improving identity preservation, target age accuracy, and temporal smoothness—both in static image and video-based age transformation tasks—outperforming current state-of-the-art methods.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Multiagent Systems: Adversarial Agents

Application Category

• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Facial aging is a complex process, highly dependent on multiple factors like gender, ethnicity, lifestyle, etc., making it extremely challenging to learn a global aging prior to predict aging for any individual accurately. Existing techniques often produce realistic and plausible aging results, but the re-aged images often do not resemble the person's appearance at the target age and thus need personalization. In many practical applications of virtual aging, e.g. VFX in movies and TV shows, access to a personal photo collection of the user depicting aging in a small time interval (20$sim$40 years) is often available. However, naive attempts to personalize global aging techniques on personal photo collections often fail. Thus, we propose MyTimeMachine (MyTM), which combines a global aging prior with a personal photo collection (using as few as 50 images) to learn a personalized age transformation. We introduce a novel Adapter Network that combines personalized aging features with global aging features and generates a re-aged image with StyleGAN2. We also introduce three loss functions to personalize the Adapter Network with personalized aging loss, extrapolation regularization, and adaptive w-norm regularization. Our approach can also be extended to videos, achieving high-quality, identity-preserving, and temporally consistent aging effects that resemble actual appearances at target ages, demonstrating its superiority over state-of-the-art approaches.

Problem

• Personalized facial aging prediction using individual photos
• Combining global and personal aging features for accuracy
• Achieving identity-preserving aging effects in images and videos

Innovation

• Combines global aging prior with personal photos
• Uses Adapter Network with StyleGAN2
• Introduces three personalized loss functions