Focal Frequency Loss for Generative Models

Despite the remarkable success of generative models in creating photorealistic images using deep neural networks, gaps could still exist between the real and generated images, especially in the frequency domain. In this study, we find that narrowing the frequency domain gap can ameliorate the image synthesis quality further. To this end, we propose the focal frequency loss, a novel objective function that brings optimization of generative models into the frequency domain. The proposed loss allows the model to dynamically focus on the frequency components that are hard to synthesize by down-weighting the easy frequencies. This objective function is complementary to existing spatial losses, offering great impedance against the loss of important frequency information due to the inherent crux of neural networks. We demonstrate the versatility and effectiveness of focal frequency loss to improve various baselines in both perceptual quality and quantitative performance.

https://arxiv.org/pdf/2012.12821.pdf

虽然深度学习生成模型已经在图像生成任务中取得了令人瞩目的进展,但是在真实和生成图像之间还存在一定的区别,特别是在频域。在本文中,我们专注于减小上述频域的差别并且提高生成图像的质量。最后,我们提出了焦点频率损失,一种在频率域进行优化的目标函数。我们提出的顺势函数使得模型可以动态地关注不同地频率域,并且将难以生成的部分降维到容易生成的频率域。上述目标函数作为现有空间损失函数的补充,它解决了现有神经网络存在的损失重要频率信息的问题。我们通过在多个基线上比较直觉质量和量化性能展示了焦点频率损失函数的通用性和有效性。

发表评论

邮箱地址不会被公开。 必填项已用*标注