Recursive Chaining of Reversible Image-to-image Translators For Face Aging
Lists
Only you see this
Abstract
This paper addresses the modeling and simulation of progressive changes over time, such as human face aging. By treating the age phases as a sequence of image domains, we construct a chain of transformers that map images from one age domain to the next. Leveraging recent adversarial image translation methods, our approach requires no training samples of the same individual at different ages. Here, the model must be flexible enough to translate a child face to a young adult, and all the way through the adulthood to old age. We find that some transformers in the chain can be recursively applied on their own output to cover multiple phases, compressing the chain. The structure of the chain also unearths information about the underlying physical process. We demonstrate the performance of our method with precise and intuitive metrics, and visually match with the face aging state-of-the-art.
BibTeX
@inproceedings{heljakka2018recursive,
author = {Ari Heljakka and Arno Solin and Juho Kannala},
title = {{Recursive Chaining of Reversible Image-to-image Translators For Face Aging}},
booktitle = {ACIVS},
year = {2018},
doi = {10.1007/978-3-030-01449-0\_26},
}| BiTrackGAN: Cascaded CycleGANs to Constraint Face Aging | arXiv · 2023 |
| Triple-GAN: Progressive Face Aging with Triple Translation Loss | Workshops @ CVPR · 2020 |
| Recurrent Face Aging | CVPR · 2016 |
| Face Aging with Contextual Generative Adversarial Nets | arXiv · 2018 |
| PFA-GAN: Progressive Face Aging With Generative Adversarial Network | arXiv · 2020 |
| Dual Conditional GANs for Face Aging and Rejuvenation | IJCAI · 2018 |