Compositing foreground and background using variational autoencoders
Compositing foreground and background using variational autoencoders
We consider the problem of composing images by combining an arbitrary foreground object to some background. To achieve this we use a factorized latent space. Thus we introduce a model called the “Background and Foreground VAE” (BFVAE) that can combine arbitrary foreground and background from an image dataset to generate unseen images. To enhance the quality of the generated images we also propose a VAE-GAN mixed model called “Latent Space Renderer-GAN” (LSR-GAN). This substantially reduces the blurriness of BFVAE images.
Disentanglement, Representation learning, VAE
553-566
Prugel-Bennett, Adam
b107a151-1751-4d8b-b8db-2c395ac4e14e
Zeng, Zezhen
d340d998-568a-434f-95eb-ef39ee335912
Hare, Jonathon
65ba2cda-eaaf-4767-a325-cd845504e5a9
2 June 2022
Prugel-Bennett, Adam
b107a151-1751-4d8b-b8db-2c395ac4e14e
Zeng, Zezhen
d340d998-568a-434f-95eb-ef39ee335912
Hare, Jonathon
65ba2cda-eaaf-4767-a325-cd845504e5a9
Prugel-Bennett, Adam, Zeng, Zezhen and Hare, Jonathon
(2022)
Compositing foreground and background using variational autoencoders.
El Yacoubi, Mounîm, Granger, Eric, Yuen, Pong Chi, Pal, Umapada and Vincent, Nicole
(eds.)
In Pattern Recognition and Artificial Intelligence : Third International Conference, ICPRAI 2022, Paris, France, June 1–3, 2022, Proceedings, Part I.
vol. 13363,
Springer Cham.
.
(doi:10.1007/978-3-031-09037-0_45).
Record type:
Conference or Workshop Item
(Paper)
Abstract
We consider the problem of composing images by combining an arbitrary foreground object to some background. To achieve this we use a factorized latent space. Thus we introduce a model called the “Background and Foreground VAE” (BFVAE) that can combine arbitrary foreground and background from an image dataset to generate unseen images. To enhance the quality of the generated images we also propose a VAE-GAN mixed model called “Latent Space Renderer-GAN” (LSR-GAN). This substantially reduces the blurriness of BFVAE images.
Text
sub_32
- Accepted Manuscript
More information
Accepted/In Press date: 15 March 2022
Published date: 2 June 2022
Additional Information:
Publisher Copyright:
© 2022, Springer Nature Switzerland AG.
Keywords:
Disentanglement, Representation learning, VAE
Identifiers
Local EPrints ID: 468256
URI: http://eprints.soton.ac.uk/id/eprint/468256
ISSN: 0302-9743
PURE UUID: fa9ded67-5f4b-45e8-b029-2360bc82c650
Catalogue record
Date deposited: 09 Aug 2022 16:33
Last modified: 06 Jun 2024 04:12
Export record
Altmetrics
Contributors
Author:
Adam Prugel-Bennett
Author:
Zezhen Zeng
Author:
Jonathon Hare
Editor:
Mounîm El Yacoubi
Editor:
Eric Granger
Editor:
Pong Chi Yuen
Editor:
Umapada Pal
Editor:
Nicole Vincent
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics