Towards photographic image manipulation with balanced growing of generative autoencoders

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Abstract

We present a generative autoencoder that provides fast encoding, faithful reconstructions (e.g. retaining the identity of a face), sharp generated/reconstructed samples in high resolutions, and a well-structured latent space that supports semantic manipulation of the inputs. There are no current autoencoder or GAN models that satisfactorily achieve all of these. We build on the progressively growing autoencoder model PIONEER , for which we completely alter the training dynamics based on a careful analysis of recently introduced normalization schemes. We show significantly improved visual and quantitative results for face identity conservation in CELEBA-HQ. Our model achieves state-of-the-art disentanglement of latent space, both quantitatively and via realistic image attribute manipulations. On the LSUN Bedrooms dataset, we improve the disentanglement performance of the vanilla PIONEER, despite having a simpler model. Overall, our results indicate that the PIONEER networks provide a way towards photorealistic face manipulation.

Original languageEnglish
Title of host publicationProceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020
PublisherIEEE
Pages3109-3118
Number of pages10
ISBN (Electronic)9781728165530
DOIs
Publication statusPublished - Mar 2020
MoE publication typeA4 Article in a conference publication
EventIEEE Winter Conference on Applications of Computer Vision - Snowmass Village, United States
Duration: 1 Mar 20205 Mar 2020

Conference

ConferenceIEEE Winter Conference on Applications of Computer Vision
Abbreviated titleWACV
CountryUnited States
CitySnowmass Village
Period01/03/202005/03/2020

Fingerprint Dive into the research topics of 'Towards photographic image manipulation with balanced growing of generative autoencoders'. Together they form a unique fingerprint.

  • Equipment

    Science-IT

    Mikko Hakala (Manager)

    School of Science

    Facility/equipment: Facility

  • Cite this

    Heljakka, A., Solin, A., & Kannala, J. (2020). Towards photographic image manipulation with balanced growing of generative autoencoders. In Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020 (pp. 3109-3118). [9093375] IEEE. https://doi.org/10.1109/WACV45572.2020.9093375