Generative adversarial networks (GANs) are successfully used for image synthesis but are known to face instability during training. In contrast, probabilistic diffusion models (DMs) are stable and generate high-quality images, at the cost of an expensive sampling procedure. In this paper, we introduce a simple method to allow GANs to stably converge to their theoretical optimum, while bringing in the denoising machinery from DMs. These models are combined into a simpler model (ATME) that only requires a forward pass during inference, making predictions cheaper and more accurate than DMs and popular GANs. ATME breaks an information asymmetry existing in most GAN models in which the discriminator has spatial knowledge of where the generator is failing. To restore the information symmetry, the generator is endowed with knowledge of the entropic state of the discriminator, which is leveraged to allow the adversarial game to converge towards equilibrium. We demonstrate the power of our method in several image-to-image translation tasks, showing superior performance than state-of-the-art methods at a lesser cost. Code is available at https://github.com/DLR-MI/atme

翻译：摘要：生成对抗网络（GANs）成功用于图像合成，但已知在训练过程中存在不稳定性。相比之下，概率扩散模型（DMs）稳定且能生成高质量图像，但代价是昂贵的采样过程。本文提出一种简单方法，使GANs能够稳定收敛到其理论最优状态，同时引入DMs的去噪机制。这些模型被整合为一个更简洁的模型（ATME），在推理时仅需前向传播，使得预测比DMs和主流GANs更廉价且更精确。ATME打破了大多数GAN模型中存在的信息不对称性，即判别器掌握生成器失效的空间位置信息。为恢复信息对称性，生成器被赋予判别器熵状态的知识，从而利用这一信息促使对抗博弈收敛至均衡。我们在多个图像到图像翻译任务中展示了该方法的能力，在更低成本下取得了优于现有最优方法的性能。代码见 https://github.com/DLR-MI/atme