The Aging Multiverse: Generating Condition-Aware Facial Aging Tree via Training-Free Diffusion

2025-06-26

AI Summary

This work addresses the limitations of single-trajectory aging and the absence of external factor control (e.g., environment, health, lifestyle) in single-image facial age progression. We propose a training-free, condition-aware aging tree generation method built upon diffusion-based image editing. Our approach integrates attention map mixing and Simulated Aging Regularization to jointly optimize identity preservation, age accuracy, and multi-dimensional conditional controllability. To our knowledge, this is the first method to construct an interpretable, multi-branch facial aging tree structure, enabling fine-grained and diverse aging path synthesis. Quantitative evaluation demonstrates state-of-the-art performance in identity preservation, aging realism, and conditional alignment. A user study further confirms its significant superiority over existing age progression and facial editing methods.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

We introduce the Aging Multiverse, a framework for generating multiple plausible facial aging trajectories from a single image, each conditioned on external factors such as environment, health, and lifestyle. Unlike prior methods that model aging as a single deterministic path, our approach creates an aging tree that visualizes diverse futures. To enable this, we propose a training-free diffusion-based method that balances identity preservation, age accuracy, and condition control. Our key contributions include attention mixing to modulate editing strength and a Simulated Aging Regularization strategy to stabilize edits. Extensive experiments and user studies demonstrate state-of-the-art performance across identity preservation, aging realism, and conditional alignment, outperforming existing editing and age-progression models, which often fail to account for one or more of the editing criteria. By transforming aging into a multi-dimensional, controllable, and interpretable process, our approach opens up new creative and practical avenues in digital storytelling, health education, and personalized visualization.

Problem

• Generating diverse facial aging paths from one image
• Modeling aging with external factors like lifestyle
• Balancing identity, age accuracy, and condition control

Innovation

• Training-free diffusion for diverse aging paths
• Attention mixing for balanced editing control
• Simulated Aging Regularization stabilizes edits