Towards Photographic Image Manipulation with Balanced Growing of Generative Autoencoders
We build on recent advances in progressively growing generative autoencoder models. These models can encode and reconstruct existing images, and generate novel ones, at resolutions comparable to Generative Adversarial Networks (GANs), while consisting only of a single encoder and decoder network. The ability to reconstruct and arbitrarily modify existing samples such as images separates autoencoder models from GANs, but the output quality of image autoencoders has remained inferior. The recently proposed PIONEER autoencoder can reconstruct faces in the $256{\times}256$ CelebAHQ dataset, but like IntroVAE, another recent method, it often loses the identity of the person in the process. We propose an improved and simplified version of PIONEER and show significantly improved quality and preservation of the face identity in CelebAHQ, both visually and quantitatively. We also show evidence of state-of-the-art disentanglement of the latent space of the model, both quantitatively and via realistic image feature manipulations. On the LSUN Bedrooms dataset, our model also improves the results of the original PIONEER. Overall, our results indicate that the PIONEER networks provide a way to photorealistic face manipulation.
NurtureToken New!

Token crowdsale for this paper ends in

Buy Nurture Tokens

Authors

Are you an author of this paper? Check the Twitter handle we have for you is correct.

Ari Heljakka (edit)
Arno Solin (edit)
Juho Kannala (add twitter)
Ask The Authors

Ask the authors of this paper a question or leave a comment.

Read it. Rate it.
#1. Which part of the paper did you read?

#2. The paper contains new data or analyses that is openly accessible?
#3. The conclusion is supported by the data and analyses?
#4. The conclusion is of scientific interest?
#5. The result is likely to lead to future research?

Github
User:
None (add)
Repo:
None (add)
Stargazers:
0
Forks:
0
Open Issues:
0
Network:
0
Subscribers:
0
Language:
None
Youtube
Link:
None (add)
Views:
0
Likes:
0
Dislikes:
0
Favorites:
0
Comments:
0
Other
Sample Sizes (N=):
Inserted:
Words Total:
Words Unique:
Source:
Abstract:
None
04/14/19 06:02PM
7,539
2,324
Tweets
AriHeljakka: New preprint 'Towards Photographic Image Manipulation with Balanced Growing of Generative Autoencoders' with @ArnoSolin and Juho Kannala. Improved latent representations for eg. manipulation of single input images. Project: https://t.co/bnkUm7aCdi arXiv: https://t.co/uskqF6bcYK https://t.co/VhEBgMFM06
arxiv_cscv: Towards Photographic Image Manipulation with Balanced Growing of Generative Autoencoders https://t.co/Nv7lehfRIK
arxiv_cscv: Towards Photographic Image Manipulation with Balanced Growing of Generative Autoencoders https://t.co/Nv7legYgRc
arnosolin: New preprint 'Towards Photographic Image Manipulation with Balanced Growing of Generative Autoencoders' with @AriHeljakka and Juho. Example of manipulating the latent space of an input image for smile and orientation. Videos: https://t.co/8ruRmNL5Ob arXiv: https://t.co/9YnOsLswtM https://t.co/PTzOrU1CDX
arxivml: "Towards Photographic Image Manipulation with Balanced Growing of Generative Autoencoders", Ari Heljakka, Arno Soliā€¦ https://t.co/qPs0LjIcy5
arxiv_cs_LG: Towards Photographic Image Manipulation with Balanced Growing of Generative Autoencoders. Ari Heljakka, Arno Solin, and Juho Kannala https://t.co/26pWRmt9XO
BrundageBot: Towards Photographic Image Manipulation with Balanced Growing of Generative Autoencoders. Ari Heljakka, Arno Solin, and Juho Kannala https://t.co/pKqvhXeoqP
Images
Related