A Style-Based Generator Architecture for Generative Adversarial Networks • 著者: T. Karras1, S. Laine1, T. Aila1 • 所属: 1) NVIDIA • 特徴: 従来に⽐べて安定的な⾼解像度画像⽣成 & 滑らかな潜在空間 • StyleGAN2 • タイトル: Analyzing and Improving the Image Quality of StyleGAN • 著者: T. Karras1, S. Laine1, M. Aittala1, J. Hellsten1, J. Lehtinen1,2, T. Aila1 • 所属: 1) NVIDIA, 2) Aalto University • 特徴: StyleGAN特有のアーティファクトを除去
al. ICLR 2019] • Brock, Andrew, Jeff Donahue, and Karen Simonyan. "Large scale gan training for high fidelity natural image synthesis." arXiv preprint arXiv:1809.11096 (2018). • [T. Karras et al. CVPR 2019] • Karras, Tero, Samuli Laine, and Timo Aila. "A style-based generator architecture for generative adversarial networks." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. • [T. Karras et al. 2019] • Karras, Tero, et al. "Analyzing and improving the image quality of stylegan." arXiv preprint arXiv:1912.04958 (2019). • [X. Huang et al. ICCV 2017] • Huang, Xun, and Serge Belongie. "Arbitrary style transfer in real-time with adaptive instance normalization." Proceedings of the IEEE International Conference on Computer Vision. 2017. • [R. Zhang et al. CVPR 2018] • Zhang, Richard, et al. "The unreasonable effectiveness of deep features as a perceptual metric." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018.