arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2008.11977cs.CVeess.IV
收藏

用于人脸超分辨率的边缘和身份保持网络

Edge and Identity Preserving Network for Face Super-Resolution

Sungkyunkwan University(成均馆大学);Xidian University(西安电子科技大学);Hana Institute of Technology(韩亚技术研究院)

Jonghyun Kim, Gen Li, Inyong Yun, Cheolkon Jung, Joongkyu Kim

摘要:

人脸超分辨率(SR)已成为视频监控和身份识别等安全解决方案中不可或缺的功能,但人脸成分的畸变是其中的一大挑战,目前大多数方法都是利用人脸先验知识和深度神经网络。这些方法需要额外的标签,更长的训练时间和更大的计算内存。在本文中,我们提出了一种新的边缘和身份保持网络的脸SR网络,命名为EIPNet,以最大限度地减少失真,利用一个轻量级的边缘块和身份信息。我们提出了一个边缘块来提取感知边缘信息,并将其连接到多个尺度的原始特征图。该结构在重建中逐渐提供边缘信息以聚合局部和全局结构信息。此外,我们定义了一个身份损失函数,以保持识别的SR图像。身份损失函数比较SR图像和它们的地面真值之间的特征分布,以恢复SR图像中的身份。此外,我们提供了一个亮度-色度误差(LCE)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分量来减少颜色信息的依赖性,而且还使我们的网络能够在RGB和YUV两个颜色空间中反映SR图像及其地面真实值之间的差异。所提出的方法有助于所提出的SR网络精心恢复面部组件,并生成具有轻量级网络结构的高质量8倍缩放SR图像。此外,我们的网络能够在GTX 1080Ti GPU上以215 fps重建128 x128 SR图像。大量的实验表明,我们的网络在两个具有挑战性的数据集:CelebA和VGGFace 2上的定性和定量性能优于最先进的方法。

英文摘要:

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.

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。

↑