Details

Autor(en) / Beteiligte

• Gu, Shuyang
• Bao, Jianmin
• Chen, Dong
• Wen, Fang
• Bischof, Horst
• Frahm, Jan-Michael
• Brox, Thomas
• Vedaldi, Andrea

Titel

GIQA: Generated Image Quality Assessment

Ist Teil von

• Computer Vision - ECCV 2020, 2020, Vol.12356, p.369-385

Ort / Verlag

Switzerland: Springer International Publishing AG

Erscheinungsjahr

2020

Link zum Volltext

Quelle

Alma/SFX Local Collection

Beschreibungen/Notizen

• Generative adversarial networks (GANs) achieve impressive results today, but not all generated images are perfect. A number of quantitative criteria have recently emerged for generative models, but none of them are designed for a single generated image. In this paper, we propose a new research topic, Generated Image Quality Assessment (GIQA), which quantitatively evaluates the quality of each generated image. We introduce three GIQA algorithms from two perspectives: learning-based and data-based. We evaluate a number of images generated by various recent GAN models on different datasets and demonstrate that they are consistent with human assessments. Furthermore, GIQA is available for many applications, like separately evaluating the realism and diversity of generative models, and enabling online hard negative mining (OHEM) in the training of GANs to improve the results.