论文标题
模糊，噪声和压缩强大的生成对抗网络
Blur, Noise, and Compression Robust Generative Adversarial Networks
论文作者
论文摘要
生成的对抗网络（GAN）由于其复制图像的能力而引起了很大的关注。但是，尽管以模糊，噪声和压缩形式的图像退化，但它们仍可以忠实地重新创建训练图像，从而产生类似降级的图像。为了解决这个问题，最近提出的噪声强大的gan（NR-GAN）通过证明使用包含图像和噪声发生器的两个驱动器模型直接从嘈杂图像中学习清洁图像发生器的能力，从而提供了部分解决方案。但是，它的应用仅限于噪声，由于其加性和可逆的特性，它相对易于分解，并且以模糊，压缩和所有组合的形式将其应用于不可逆的图像退化，这仍然是一个挑战。为了解决这些问题，我们建议可以直接从退化的图像中学习干净的图像发生器的模糊，噪声和压缩稳健的GAN（BNCR-GAN），而无需了解降解参数（例如，模糊内核类型，噪声量或质量因子值）。受NR-GAN的启发，BNCR-GAN使用了由图像，模糊，噪声和质量因子发电机组成的多生元素模型。但是，与NR-GAN相反，为了解决不可逆的特征，我们在降级前后介绍了以数据驱动的方式调整降解强度值的体系结构。此外，为了抑制模糊，噪声和压缩的组合引起的不确定性，我们引入了自适应一致性损失，从而根据降解强度施加了不可逆的降解过程之间的一致性。我们通过对CIFAR-10的大规模比较研究和FFHQ的一般分析来证明BNCR-GAN的有效性。此外，我们证明了BNCR-GAN在图像恢复中的适用性。
Generative adversarial networks (GANs) have gained considerable attention owing to their ability to reproduce images. However, they can recreate training images faithfully despite image degradation in the form of blur, noise, and compression, generating similarly degraded images. To solve this problem, the recently proposed noise robust GAN (NR-GAN) provides a partial solution by demonstrating the ability to learn a clean image generator directly from noisy images using a two-generator model comprising image and noise generators. However, its application is limited to noise, which is relatively easy to decompose owing to its additive and reversible characteristics, and its application to irreversible image degradation, in the form of blur, compression, and combination of all, remains a challenge. To address these problems, we propose blur, noise, and compression robust GAN (BNCR-GAN) that can learn a clean image generator directly from degraded images without knowledge of degradation parameters (e.g., blur kernel types, noise amounts, or quality factor values). Inspired by NR-GAN, BNCR-GAN uses a multiple-generator model composed of image, blur-kernel, noise, and quality-factor generators. However, in contrast to NR-GAN, to address irreversible characteristics, we introduce masking architectures adjusting degradation strength values in a data-driven manner using bypasses before and after degradation. Furthermore, to suppress uncertainty caused by the combination of blur, noise, and compression, we introduce adaptive consistency losses imposing consistency between irreversible degradation processes according to the degradation strengths. We demonstrate the effectiveness of BNCR-GAN through large-scale comparative studies on CIFAR-10 and a generality analysis on FFHQ. In addition, we demonstrate the applicability of BNCR-GAN in image restoration.
