https://mytimemachine.github.io

 
TOC
Abstract Method Results Acknowledgements BibTeX

MyTimeMachine: Personalized Facial Age Transformation

Luchao Qi^1, Jiaye Wu^2, Bang Gong^1, Annie N. Wang^1, David W.
Jacobs^2, Roni Sengupta^1,
^1The University of North Carolina at Chapel Hill, ^2The University
of Maryland
Paper arXiv Code (coming soon)
[teaser]

MyTimeMachine personalizes a pre-trained global aging prior using $\
sim$50 personal selfies, allowing age regression (de-aging) and age
progression (aging) with high fidelity and identity preservation.

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.

Video


Motivation: Why Age Transformation?


Method

[architectu]

Given an input face of $\textit{Oprah Winfrey}$ at 70 years old, our
adapter re-ages her face to resemble her appearance at 30, while
preserving the style of the input image. To achieve personalized
re-aging, we collect $\sim$50 images of an individual across
different ages and train an adapter network that updates the latent
code generated by the global age encoder SAM. Our adapter preserves
identity during interpolation when the target age falls within the
range of ages seen in the training data, while also extrapolating
well to unseen ages.

Animation

Age Regression (De-aging from ~70 years old)

[]
Source ~70 years old
[]
No reference available
at this age
Reference
[]
Ours (30~70)
[]
SAM
[]
Fading

Please try selecting different celebrities by clicking on the
thumbnails. Move the slider to adjust the target age.

[source] [source] [source] [source] [source] [source] [source] 
[source] [source] [source] [source] [source]
[3                   ] 00 10 20 30 40 50 60 70 80 90 100

Age Progression (Aging from ~40 years old)

[]
Source ~40 years old
[]
No reference available
at this age
Reference
[]
Ours (20~40)
[]
SAM
[]
Fading

Please try selecting different celebrities by clicking on the
thumbnails. Move the slider to adjust the target age.

[source] [source] [source] [source] [source] [source] [source]
[3                   ] 00 10 20 30 40 50 60 70 80 90 100

Acknowledgements

We thank Noah Frahm for reviewing early drafts and suggesting helpful
improvements. We thank Yiran Xu for thoughtful discussions and
feedback during the course of this research.

BibTeX

@misc{qi2024mytimemachinepersonalizedfacialage,
      title={MyTimeMachine: Personalized Facial Age Transformation},
      author={Luchao Qi and Jiaye Wu and Bang Gong and Annie N. Wang and David W. Jacobs and Roni Sengupta},
      year={2024},
      eprint={2411.14521},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2411.14521},
  }

 

This website is licensed under a Creative Commons
Attribution-ShareAlike 4.0 International License.

Website template credits to Nerfies, and Reconfusion.

Back to Top