论文标题
边缘和身份保存网络，用于面部超分辨率
Edge and Identity Preserving Network for Face Super-Resolution
论文作者
论文摘要
面部超分辨率（SR）已成为视频监视和识别系统等安全解决方案中必不可少的功能，但是面部组件中的失真是其中的巨大挑战。大多数最先进的方法都使用了具有深神经网络的面部先验。这些方法需要额外的标签，更长的训练时间和更大的计算记忆。在本文中，我们提出了一个新颖的边缘和身份，以保留面部SR网络（称为EIPNET）的网络，以通过利用轻质边缘块和身份信息来最大程度地减少失真。我们提出一个边缘块来提取感知边缘信息，并将其与多个尺度的原始特征图相连。该结构逐渐提供重建中的优势信息，以汇总本地和全球结构信息。此外，我们定义了一个身份损失函数，以保留SR图像的识别。身份损失函数比较SR图像与其地面真相之间的特征分布，以恢复SR图像中的身份。此外，我们提供了亮度 - 巧合误差（LCE），以分别推断SR图像中的亮度和颜色信息。 LCE方法不仅通过划分亮度和颜色成分来降低颜色信息的依赖性，而且还使我们的网络能够在RGB和YUV的两个颜色空间中反映SR图像及其地面真相之间的差异。所提出的方法促进了所提出的SR网络，以精心恢复面部组件并生成具有轻量级网络结构的高质量的8X缩放SR图像。此外，我们的网络能够在GTX 1080TI GPU上重建具有215 fps的128x128 SR映像。广泛的实验表明，在两个具有挑战性的数据集上，我们的网络在定性和定量上优于最先进的方法：Celeba和Vggface2。
Face super-resolution (SR) has become an indispensable function in security solutions such as video surveillance and identification system, but the distortion in facial components is a great challenge in it. Most state-of-the-art methods have utilized facial priors with deep neural networks. These methods require extra labels, longer training time, and larger computation memory. In this paper, we propose a novel Edge and Identity Preserving Network for Face SR Network, named as EIPNet, to minimize the distortion by utilizing a lightweight edge block and identity information. We present an edge block to extract perceptual edge information, and concatenate it to the original feature maps in multiple scales. This structure progressively provides edge information in reconstruction to aggregate local and global structural information. Moreover, we define an identity loss function to preserve identification of SR images. The identity loss function compares feature distributions between SR images and their ground truth to recover identities in SR images. In addition, we provide a luminance-chrominance error (LCE) to separately infer brightness and color information in SR images. The LCE method not only reduces the dependency of color information by dividing brightness and color components but also enables our network to reflect differences between SR images and their ground truth in two color spaces of RGB and YUV. The proposed method facilitates the proposed SR network to elaborately restore facial components and generate high quality 8x scaled SR images with a lightweight network structure. Furthermore, our network is able to reconstruct an 128x128 SR image with 215 fps on a GTX 1080Ti GPU. Extensive experiments demonstrate that our network qualitatively and quantitatively outperforms state-of-the-art methods on two challenging datasets: CelebA and VGGFace2.
