论文信息 - Face Super-Resolution Through Wasserstein GANs

Face Super-Resolution Through Wasserstein GANs

Generative adversarial networks (GANs) have received a tremendous amount of attention in the past few years, and have inspired applications addressing a wide range of problems. Despite its great potential, GANs are difficult to train. Recently, a series of papers (Arjovsky & Bottou, 2017a; Arjovsky et al. 2017b; and Gulrajani et al. 2017) proposed using Wasserstein distance as the training objective and promised easy, stable GAN training across architectures with minimal hyperparameter tuning. In this paper, we compare the performance of Wasserstein distance with other training objectives on a variety of GAN architectures in the context of single image super-resolution. Our results agree that Wasserstein GAN with gradient penalty (WGAN-GP) provides stable and converging GAN training and that Wasserstein distance is an effective metric to gauge training progress.

Zhimin Chen | Yuguang Tong | Zhimin Chen | Yuguang Tong

[1] Alexei A. Efros,et al. Generative Visual Manipulation on the Natural Image Manifold , 2016, ECCV.

[2] Ian J. Goodfellow,et al. On distinguishability criteria for estimating generative models , 2014, ICLR.

[3] Léon Bottou,et al. Towards Principled Methods for Training Generative Adversarial Networks , 2017, ICLR.

[4] Bernt Schiele,et al. Generative Adversarial Text to Image Synthesis , 2016, ICML.

[5] Sergey Levine,et al. A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models , 2016, ArXiv.

[6] Xiaogang Wang,et al. Deep Learning Face Attributes in the Wild , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[7] Ian J. Goodfellow,et al. NIPS 2016 Tutorial: Generative Adversarial Networks , 2016, ArXiv.

[8] Dimitris N. Metaxas,et al. StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[9] Aaron C. Courville,et al. Improved Training of Wasserstein GANs , 2017, NIPS.

[10] Alexei A. Efros,et al. Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).