Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks

CycleGAN：使用循环一致损失实现无配对数据的图像转换.

Wasserstein GANs Work Because They Fail (to Approximate the Wasserstein Distance)

WGAN的表现与Wasserstein距离的近似程度没有必然联系.

How Well Do WGANs Estimate the Wasserstein Metric?

讨论WGAN与Wasserstein距离的近似程度.

GraN-GAN: Piecewise Gradient Normalization for Generative Adversarial Networks

GraN-GAN：在WGAN中引入分段线性的梯度归一化.

Gradient Normalization for Generative Adversarial Networks

GN-GAN：在WGAN中引入梯度归一化.

Wasserstein Divergence for GANs

WGAN-div：通过Wasserstein散度构造GAN.