Style-Based Age Manipulation

Abstract

The task of age transformation illustrates the change of an individual's appearance over time. Accurately modeling this complex transformation over an input facial image is extremely challenging as it requires making convincing and possibly large changes to facial features and head shape, while still preserving the input identity. In this work, we present an image-to-image translation method that learns to directly encode real facial images into the latent space of a pre-trained unconditional GAN (e.g., StyleGAN) subject to a given aging shift. We employ a pre-trained age regression network used to explicitly guide the encoder in generating the latent codes corresponding to the desired age. In this formulation, our method approaches the continuous aging process as a regression task between the input age and desired target age, providing fine-grained control over the generated image. Moreover, unlike other approaches that operate solely in the latent space using a prior on the path controlling age, our method learns a more disentangled, non-linear path. Finally, we demonstrate that the end-to-end nature of our approach, coupled with the rich semantic latent space of StyleGAN, allows for further editing of the generated images. Qualitative and quantitative evaluations show the advantages of our method compared to state-of-the-art approaches.

Demo

Replicate have designed a demo for SAM where you can easily upload an image and run SAM on a desired set of ages!
Check out the demo here!

Overview

We introduce SAM --- Style-based Age Manipulaton, a technique for modeling fine-grained age transformation from a single input facial image. SAM pairs a pre-trained, fixed StyleGAN generator with an encoder network tasked with encoding real face images into a series of style vectors subject to the desired age change.

A pre-trained, fixed age regressor guides the encoder into generating the desired age-transformed latent codes. As a result, SAM views human aging as a regression problem to the desired target age.

Guided by the age regressor, SAM learns non-linear paths able to better disentangle age from other attributes (pose, hair style, etc.). These paths are well-suited to the complex nature of StyleGAN’s latent space manifold.

Results

Below we show aging results between the ages 0 and 100.

Acknowledgements

We would like to thank Elad Richardson, Kfir Goldberg, Ohad Fried, Yotam Nitzan, and Zongze Wu for their fruitful discussions and early feedback. We would also like to thank the anonymous reviewers for their insightful comments and constructive remarks. This work was supported in part by the Israel Science Foundation under Grant No. 2366/16 and Grant No. 2492/20.

Reference

@article{alaluf2021matter, author = {Alaluf, Yuval and Patashnik, Or and Cohen-Or, Daniel}, title = {Only a Matter of Style: Age Transformation Using a Style-Based Regression Model}, journal = {ACM Trans. Graph.}, issue_date = {August 2021}, volume = {40}, number = {4}, year = {2021}, articleno = {45}, publisher = {Association for Computing Machinery}, url = {https://doi.org/10.1145/3450626.3459805} }