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.
翻译:由于具有复制图像的能力,生成对抗性网络(GANs)已获得相当大的关注,然而,它们能够忠实地重建培训图像,尽管图像以模糊、噪声和压缩的形式退化,产生同样退化的图像。为了解决这个问题,最近提出的噪音强的GAN(NR-GAN)提供了部分的解决方案,通过使用由图像和噪声生成器组成的两个生成器模型,展示直接从噪音图像中学习清洁图像生成器的能力。然而,其应用限于噪音,由于其添加性和可逆性特点,以及它以模糊、压缩和组合的形式应用于不可逆转的图像降解,仍然是一项挑战。为了解决这些问题,我们提出了模糊、噪音和压缩强的GAN(BCR-GAN),它能够直接从不熟悉退化参数的退化图像中学习清洁图像生成器。 然而,我们通过NR-GAN、BCR-NCR-G的粘力和质因子值的混合,在图像、粘性变压性变压过程中,我们从变压性变压到变压的图像、变压性变压性数据中,我们从变压性变压到变压性变压数据的系统,我们从变压到变压性变压性变压数据到变压性数据学到变压数据。