Custom Structure Preservation in Face Aging

07/22/2022
by   Guillermo Gomez-Trenado, et al.
0

In this work, we propose a novel architecture for face age editing that can produce structural modifications while maintaining relevant details present in the original image. We disentangle the style and content of the input image and propose a new decoder network that adopts a style-based strategy to combine the style and content representations of the input image while conditioning the output on the target age. We go beyond existing aging methods allowing users to adjust the degree of structure preservation in the input image during inference. To this purpose, we introduce a masking mechanism, the CUstom Structure Preservation module, that distinguishes relevant regions in the input image from those that should be discarded. CUSP requires no additional supervision. Finally, our quantitative and qualitative analysis which include a user study, show that our method outperforms prior art and demonstrates the effectiveness of our strategy regarding image editing and adjustable structure preservation. Code and pretrained models are available at https://github.com/guillermogotre/CUSP.

READ FULL TEXT

page 10

page 25

page 28

page 29

page 30

page 31

page 32

page 34

research
09/20/2023

Face Aging via Diffusion-based Editing

In this paper, we address the problem of face aging: generating past or ...
research
06/15/2023

Personalized Image Enhancement Featuring Masked Style Modeling

We address personalized image enhancement in this study, where we enhanc...
research
04/26/2022

Expanding the Latent Space of StyleGAN for Real Face Editing

Recently, a surge of face editing techniques have been proposed to emplo...
research
05/08/2023

ReGeneration Learning of Diffusion Models with Rich Prompts for Zero-Shot Image Translation

Large-scale text-to-image models have demonstrated amazing ability to sy...
research
05/27/2023

Text-to-image Editing by Image Information Removal

Diffusion models have demonstrated impressive performance in text-guided...
research
03/23/2021

DeFLOCNet: Deep Image Editing via Flexible Low-level Controls

User-intended visual content fills the hole regions of an input image in...
research
02/18/2021

DSRN: an Efficient Deep Network for Image Relighting

Custom and natural lighting conditions can be emulated in images of the ...

Please sign up or login with your details

Forgot password? Click here to reset