LatentKeypointGAN: Controlling Images via Latent Keypoints – Extended Abstract

05/06/2022
by   Xingzhe He, et al.
0

Generative adversarial networks (GANs) can now generate photo-realistic images. However, how to best control the image content remains an open challenge. We introduce LatentKeypointGAN, a two-stage GAN internally conditioned on a set of keypoints and associated appearance embeddings providing control of the position and style of the generated objects and their respective parts. A major difficulty that we address is disentangling the image into spatial and appearance factors with little domain knowledge and supervision signals. We demonstrate in a user study and quantitative experiments that LatentKeypointGAN provides an interpretable latent space that can be used to re-arrange the generated images by re-positioning and exchanging keypoint embeddings, such as generating portraits by combining the eyes, and mouth from different images. Notably, our method does not require labels as it is self-supervised and thereby applies to diverse application domains, such as editing portraits, indoor rooms, and full-body human poses.

READ FULL TEXT

page 1

page 3

page 4

research
03/29/2021

LatentKeypointGAN: Controlling GANs via Latent Keypoints

Generative adversarial networks (GANs) have attained photo-realistic qua...
research
03/19/2022

A naive method to discover directions in the StyleGAN2 latent space

Several research groups have shown that Generative Adversarial Networks ...
research
04/12/2023

VidStyleODE: Disentangled Video Editing via StyleGAN and NeuralODEs

We propose VidStyleODE, a spatiotemporally continuous disentangled Video...
research
03/14/2022

InsetGAN for Full-Body Image Generation

While GANs can produce photo-realistic images in ideal conditions for ce...
research
03/11/2021

HumanGAN: A Generative Model of Humans Images

Generative adversarial networks achieve great performance in photorealis...
research
05/06/2020

Generating Memorable Images Based on Human Visual Memory Schemas

This research study proposes using Generative Adversarial Networks (GAN)...
research
02/23/2021

Generative Modelling of BRDF Textures from Flash Images

We learn a latent space for easy capture, semantic editing, consistent i...

Please sign up or login with your details

Forgot password? Click here to reset