Only a matter of style: age transformation using a style-based regression model

By Yuval Alaluf, Or Patashnik, Daniel Cohen-Or. 2021

176 citations recorded by the source corpus.

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, 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 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 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. Code is available at our project page: https://yuval-alaluf.github.io/SAM.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery (2021, background): “Specific edits, such as virtual try-on [21] and aging [2] have also been explored.”
GAN Inversion: A Survey (2021, background): “Although often regarded as an independent research field, it becomes an indispensable application of the GAN inversion [93], [125].”
Alias-Free Generative Adversarial Networks (2021, background): “They have been used for a variety of applications, including image editing [47, 53, 42, 21, 38, 3], domain translation [66, 36, 58, 41], and video generation [55, 15, 23].”
HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing (2021, background): “On the other end of the reconstruction-editability trade-off, e4e and ReStylee4e are more editable but cannot faithfully preserve the original identity, as demonstrated in the 3rd and 4th rows.”
Third Time's the Charm? Image and Video Editing with StyleGAN3 (2022, background): “Specifically, StyleGAN generators [33–36] synthesize exceed-ingly realistic images, and enable editing [4,5,9,15,42,48, 83], and image-to-image translation [46,47,55], particularly in well-structured domains.”
Adding Conditional Control to Text-to-Image Diffusion Models (2023, background): “, StyleGANs can be controlled by extra encoders [70], with more applications studied in [3, 22, 38, 39, 55, 59, 64, 70].”