读《CircleGAN: Generative Adversarial Learning across Spherical Circles》
目的:探查该方法用不同内容的图片来实现SR重建的方法;摘要:为GANs提出了一种新的判别器(基于Hypersphere embedding space),它能够通过学习超球面空间特征?来提升生成样本的真实性和多样性;Our work also adopts a hypersphere embedding space, but proposes a different strategy instructuring and learning the hypersphere, which ...
原创
2021-07-22 22:36:40 ·
2775 阅读 ·
0 评论