arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1609.04802cs.CVstat.ML
收藏

基于生成对抗网络的单幅图像超分辨率

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

Twitter(推特)

Christian Ledig, Lucas Theis, Ferenc Huszar, Jose Caballero, Andrew Cunningham, Alejandro Acosta, Andrew Aitken, Alykhan Tejani, Johannes Totz, Zehan Wang, Wenzhe Shi

摘要:

尽管使用更快、更深的卷积神经网络在单个图像超分辨率的准确性和速度上取得了突破,但一个核心问题仍然在很大程度上没有解决:当我们以大的放大因子进行超分辨率时,我们如何恢复更精细的纹理细节?基于优化的超分辨率方法的行为主要由目标函数的选择驱动。最近的工作主要集中在最小化均方重建误差。所得到的估计具有高峰值信噪比,但它们通常缺乏高频细节,并且在感知上不令人满意,因为它们无法匹配在更高分辨率下期望的保真度。在本文中,我们提出了SR GAN,一个生成对抗网络(GAN)的图像超分辨率(SR)。据我们所知,它是第一个能够推断出具有4倍放大因子的照片级真实感自然图像的框架。为了实现这一点,我们提出了一个感知损失函数,其中包括一个对抗性损失和内容损失。对抗性损失将我们的解决方案推到自然图像流形上,使用一个经过训练的神经网络来区分超分辨率图像和原始照片级真实感图像。此外,我们使用的内容损失的动机是感知相似性,而不是相似的像素空间。我们的深度残差网络能够从公共基准上的大量下采样图像中恢复照片般逼真的纹理。一个广泛的平均意见分数(MOS)测试显示,使用SRGAN的感知质量有了非常显著的提高。SRGAN获得的MOS分数更接近原始高分辨率图像的分数,而不是使用任何最先进的方法获得的分数。

英文摘要:

Despite the breakthroughs in accuracy and speed of single image super-resolution using faster and deeper convolutional neural networks, one central problem remains largely unsolved: how do we recover the finer texture details when we super-resolve at large upscaling factors? The behavior of optimization-based super-resolution methods is principally driven by the choice of the objective function. Recent work has largely focused on minimizing the mean squared reconstruction error. The resulting estimates have high peak signal-to-noise ratios, but they are often lacking high-frequency details and are perceptually unsatisfying in the sense that they fail to match the fidelity expected at the higher resolution. In this paper, we present SRGAN, a generative adversarial network (GAN) for image super-resolution (SR). To our knowledge, it is the first framework capable of inferring photo-realistic natural images for 4x upscaling factors. To achieve this, we propose a perceptual loss function which consists of an adversarial loss and a content loss. The adversarial loss pushes our solution to the natural image manifold using a discriminator network that is trained to differentiate between the super-resolved images and original photo-realistic images. In addition, we use a content loss motivated by perceptual similarity instead of similarity in pixel space. Our deep residual network is able to recover photo-realistic textures from heavily downsampled images on public benchmarks. An extensive mean-opinion-score (MOS) test shows hugely significant gains in perceptual quality using SRGAN. The MOS scores obtained with SRGAN are closer to those of the original high-resolution images than to those obtained with any state-of-the-art method.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑