Corpus ID: 3568073

Progressive Growing of GANs for Improved Quality, Stability, and Variation

@article{Karras2018ProgressiveGO,
  title={Progressive Growing of GANs for Improved Quality, Stability, and Variation},
  author={Tero Karras and Timo Aila and S. Laine and J. Lehtinen},
  journal={ArXiv},
  year={2018},
  volume={abs/1710.10196}
}
  • Tero Karras, Timo Aila, +1 author J. Lehtinen
  • Published 2018
  • Computer Science, Mathematics
  • ArXiv
  • We describe a new training methodology for generative adversarial networks. [...] Key Method We also propose a simple way to increase the variation in generated images, and achieve a record inception score of 8.80 in unsupervised CIFAR10. Additionally, we describe several implementation details that are important for discouraging unhealthy competition between the generator and discriminator. Finally, we suggest a new metric for evaluating GAN results, both in terms of image quality and variation. As an…Expand Abstract
    2,486 Citations
    Improved Consistency Regularization for GANs
    • 15
    • Highly Influenced
    • PDF
    Progressive Augmentation of GANs
    • 4
    • Highly Influenced
    • PDF
    MSG-GAN: Multi-Scale Gradients for Generative Adversarial Networks
    • Animesh Karnewar, Oliver Wang
    • Computer Science, Mathematics
    • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2020
    • 28
    • Highly Influenced
    • PDF
    Deshufflegan: A Self-Supervised Gan to Improve Structure Learning
    • 3
    • PDF
    Large Scale GAN Training for High Fidelity Natural Image Synthesis
    • 1,502
    • Highly Influenced
    • PDF
    PA-GAN: Improving GAN Training by Progressive Augmentation
    • 6
    • Highly Influenced
    Improved Techniques for Training Score-Based Generative Models
    • 25
    • Highly Influenced
    • PDF
    Stability and Diversity in Generative Adversarial Networks
    • 2
    • Highly Influenced
    MSG-GAN: Multi-Scale Gradients GAN for more stable and synchronized multi-scale image synthesis
    • 7
    • Highly Influenced

    References

    SHOWING 1-10 OF 62 REFERENCES
    Improved Techniques for Training GANs
    • 4,056
    • Highly Influential
    • PDF
    Conditional Image Synthesis with Auxiliary Classifier GANs
    • 1,530
    • Highly Influential
    • PDF
    High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
    • 1,352
    • PDF
    Improved Training of Wasserstein GANs
    • 3,939
    • Highly Influential
    • PDF
    BEGAN: Boundary Equilibrium Generative Adversarial Networks
    • 799
    • PDF
    Megapixel Size Image Creation using Generative Adversarial Networks
    • 39
    • PDF
    Energy-based Generative Adversarial Network
    • 745
    • Highly Influential
    • PDF
    Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
    • C. Ledig, L. Theis, +6 authors W. Shi
    • Computer Science, Mathematics
    • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2017
    • 4,371
    • PDF