无需训练即可生成多种可能的衰老路径，支持环境、健康等条件控制。
The Aging Multiverse: Generating Condition-Aware Facial Aging Tree via Training-Free Diffusion
- 采用无训练扩散模型，通过注意力混合调节编辑强度。
- 提出模拟老化正则化，稳定生成效果并保持身份一致性。
- 适合数字叙事、健康教育等需要可控衰老可视化的场景。
我们提出 Aging Multiverse 框架，从单张图像生成多种符合外部条件（如环境、健康、生活方式）的面部衰老轨迹。不同于以往将衰老视为单一确定路径的方法，该框架构建了可可视化多样未来的衰老树。通过无训练的扩散机制，在保持身份不变、年龄准确和条件可控之间取得平衡。核心贡献包括注意力混合策略以调节编辑强度，以及模拟老化正则化（Simulated Aging Regularization）以稳定生成过程。大量实验与用户研究显示，其在身份保留、衰老真实感和条件对齐方面均达到当前最优水平，优于现有编辑与年龄推进模型。该方法将衰老建模为多维、可控且可解释的过程，为数字叙事、健康教育及个性化可视化开辟新可能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。