Analyzing and Improving the Image Quality of StyleGAN: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

T. Karras, Samuli Laine, M. Aittala, J. Hellsten, J. Lehtinen, T. Aila

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference contributionScientificvertaisarvioitu

Abstrakti

The style-based GAN architecture (StyleGAN) yields state-of-the-art results in data-driven unconditional generative image modeling. We expose and analyze several of its characteristic artifacts, and propose changes in both model architecture and training methods to address them. In particular, we redesign the generator normalization, revisit progressive growing, and regularize the generator to encourage good conditioning in the mapping from latent codes to images. In addition to improving image quality, this path length regularizer yields the additional benefit that the generator becomes significantly easier to invert. This makes it possible to reliably attribute a generated image to a particular network. We furthermore visualize how well the generator utilizes its output resolution, and identify a capacity problem, motivating us to train larger models for additional quality improvements. Overall, our improved model redefines the state of the art in unconditional image modeling, both in terms of existing distribution quality metrics as well as perceived image quality.
AlkuperäiskieliEnglanti
OtsikkoIEEE Computer Society Conference on Computer Vision and Pattern Recognition
KustantajaIEEE
Sivut8107-8116
Sivumäärä10
DOI - pysyväislinkit
TilaJulkaistu - 2020
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaIEEE Conference on Computer Vision and Pattern Recognition - Virtual, Online
Kesto: 13 kesäkuuta 202019 kesäkuuta 2020

Julkaisusarja

NimiIEEE Computer Society Conference on Computer Vision and Pattern Recognition
KustantajaIEEE
ISSN (painettu)1063-6919
ISSN (elektroninen)2332-564X

Conference

ConferenceIEEE Conference on Computer Vision and Pattern Recognition
LyhennettäCVPR
KaupunkiVirtual, Online
Ajanjakso13/06/202019/06/2020

Sormenjälki Sukella tutkimusaiheisiin 'Analyzing and Improving the Image Quality of StyleGAN: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä