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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Gong, Bang, Qi, Luchao, Wu, Jiaye, Fu, Zhicheng, Song, Chunbo, Jacobs, David W., Nicholson, John, Sengupta, Roni
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918115952033792
author Gong, Bang
Qi, Luchao
Wu, Jiaye
Fu, Zhicheng
Song, Chunbo
Jacobs, David W.
Nicholson, John
Sengupta, Roni
author_facet Gong, Bang
Qi, Luchao
Wu, Jiaye
Fu, Zhicheng
Song, Chunbo
Jacobs, David W.
Nicholson, John
Sengupta, Roni
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_21008
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Aging Multiverse: Generating Condition-Aware Facial Aging Tree via Training-Free Diffusion
Gong, Bang
Qi, Luchao
Wu, Jiaye
Fu, Zhicheng
Song, Chunbo
Jacobs, David W.
Nicholson, John
Sengupta, Roni
Computer Vision and Pattern Recognition
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.
title The Aging Multiverse: Generating Condition-Aware Facial Aging Tree via Training-Free Diffusion
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.21008