论文标题
OMNI-GAN：关于CGAN及其他的秘密
Omni-GAN: On the Secrets of cGANs and Beyond
论文作者
论文摘要
有条件的生成对抗网络（CGAN）是生成高质量图像的强大工具，但是现有方法主要遭受不满意的性能或模式崩溃的风险。本文介绍了omni-gan，这是CGAN的一种变体，它在设计适当的歧视器时揭示了魔鬼用于训练模型。关键是要确保歧视者得到强有力的监督，以感知概念并进行中等正规化以避免崩溃。 OMNI-GAN轻松实施并与现成的编码方法（例如，隐式神经表示，INR）自由整合。实验验证了Omni-Gan和Omni-Inr-Gan在各种图像生成和恢复任务中的出色性能。特别是，Omni-Inr-GAN在Imagenet数据集上设置了新记录，其成立分别为262.85和343.22的图像尺寸为128和256，使先前的记录超过100点。此外，要利用发电机先验，Omni-Inr-GAN可以将低分辨率图像推断为任意分辨率，甚至可以提高X60+更高分辨率。代码可用。
The conditional generative adversarial network (cGAN) is a powerful tool of generating high-quality images, but existing approaches mostly suffer unsatisfying performance or the risk of mode collapse. This paper presents Omni-GAN, a variant of cGAN that reveals the devil in designing a proper discriminator for training the model. The key is to ensure that the discriminator receives strong supervision to perceive the concepts and moderate regularization to avoid collapse. Omni-GAN is easily implemented and freely integrated with off-the-shelf encoding methods (e.g., implicit neural representation, INR). Experiments validate the superior performance of Omni-GAN and Omni-INR-GAN in a wide range of image generation and restoration tasks. In particular, Omni-INR-GAN sets new records on the ImageNet dataset with impressive Inception scores of 262.85 and 343.22 for the image sizes of 128 and 256, respectively, surpassing the previous records by 100+ points. Moreover, leveraging the generator prior, Omni-INR-GAN can extrapolate low-resolution images to arbitrary resolution, even up to x60+ higher resolution. Code is available.
