What's in a Decade? Transforming Faces Through Time

Loading...
Thumbnail Image
Date
2023
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association and John Wiley & Sons Ltd.
Abstract
How can one visually characterize photographs of people over time? In this work, we describe the Faces Through Time dataset, which contains over a thousand portrait images per decade from the 1880s to the present day. Using our new dataset, we devise 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 decades-such as different hairstyles or makeup-while maintaining the identity of the input portrait. Experiments show that our method can more effectively resynthesizing portraits across time compared to state-of-theart image-to-image translation methods, as well as attribute-based and language-guided portrait editing models. Our code and data will be available at facesthroughtime.github.io.
Description

CCS Concepts: Computing methodologies -> Image manipulation; Computer graphics; Computer vision

        
@article{
10.1111:cgf.14761
, journal = {Computer Graphics Forum}, title = {{
What's in a Decade? Transforming Faces Through Time
}}, author = {
Chen, Eric Ming
and
Sun, Jin
and
Khandelwal, Apoorv
and
Lischinski, Dani
and
Snavely, Noah
and
Averbuch-Elor, Hadar
}, year = {
2023
}, publisher = {
The Eurographics Association and John Wiley & Sons Ltd.
}, ISSN = {
1467-8659
}, DOI = {
10.1111/cgf.14761
} }
Citation
Collections