论文标题
超分辨率的统一动态卷积网络以及变化降解
Unified Dynamic Convolutional Network for Super-Resolution with Variational Degradations
论文作者
论文摘要
深度卷积神经网络（CNN）在单像超分辨率（SISR）上取得了显着的结果。尽管仅考虑一次降解，但最近的研究还包括多种降解效果，以更好地反映现实世界中的情况。但是，大多数作品都采用固定的降解效果组合，甚至训练单个网络以进行不同的组合。相反，一种更实用的方法是训练单个网络以进行广泛和变化的降解。为了满足这一要求，本文提出了一个统一的网络，以适应图像间（跨图像变化）和图像内图像（空间变化）的变化。与现有作品不同，我们结合了动态卷积，这是处理不同变化的更灵活的替代方案。在具有非盲设置的SISR中，我们在合成图像和真实图像上都评估了我们的统一的变化降解动力卷积网络（UDVD），并具有广泛的变化集。定性结果证明了UDVD对各种现有作品的有效性。广泛的实验表明，我们的UDVD在合成图像和真实图像上都具有优惠或可比的性能。
Deep Convolutional Neural Networks (CNNs) have achieved remarkable results on Single Image Super-Resolution (SISR). Despite considering only a single degradation, recent studies also include multiple degrading effects to better reflect real-world cases. However, most of the works assume a fixed combination of degrading effects, or even train an individual network for different combinations. Instead, a more practical approach is to train a single network for wide-ranging and variational degradations. To fulfill this requirement, this paper proposes a unified network to accommodate the variations from inter-image (cross-image variations) and intra-image (spatial variations). Different from the existing works, we incorporate dynamic convolution which is a far more flexible alternative to handle different variations. In SISR with non-blind setting, our Unified Dynamic Convolutional Network for Variational Degradations (UDVD) is evaluated on both synthetic and real images with an extensive set of variations. The qualitative results demonstrate the effectiveness of UDVD over various existing works. Extensive experiments show that our UDVD achieves favorable or comparable performance on both synthetic and real images.
