English

What's in a Decade? Transforming Faces Through Time

Computer Vision and Pattern Recognition 2023-02-02 v3 Graphics

Abstract

How can one visually characterize people in a decade? In this work, we assemble the Faces Through Time dataset, which contains over a thousand portrait images from each decade, spanning the 1880s to the present day. Using our new dataset, we present a framework for resynthesizing portrait images across time, imagining how a portrait taken during a particular decade might have looked like, had it been taken in other decades. Our framework optimizes a family of per-decade generators that reveal subtle changes that differentiate decade--such as different hairstyles or makeup--while maintaining the identity of the input portrait. Experiments show that our method is more effective in resynthesizing portraits across time compared to state-of-the-art image-to-image translation methods, as well as attribute-based and language-guided portrait editing models. Our code and data will be available at https://facesthroughtime.github.io

Keywords

Cite

@article{arxiv.2210.06642,
  title  = {What's in a Decade? Transforming Faces Through Time},
  author = {Eric Ming Chen and Jin Sun and Apoorv Khandelwal and Dani Lischinski and Noah Snavely and Hadar Averbuch-Elor},
  journal= {arXiv preprint arXiv:2210.06642},
  year   = {2023}
}

Comments

Project Page: https://facesthroughtime.github.io

R2 v1 2026-06-28T03:30:01.547Z