arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.02427eess.IVcs.CV
收藏

真实世界人脸的超分辨率

Super-Resolution of Real-World Faces

Indian Institute of Technology, Madras(马德拉斯印度理工学院)

Saurabh Goswami, Aakanksha, Rajagopalan A. N

摘要:

真实的低分辨率(LR)人脸图像包含退化,这些退化变化太大且太复杂,以至于无法通过已知的下采样内核和信号无关噪声来捕获。因此,为了成功地超分辨真实人脸,一种方法需要对大范围的噪声、模糊、压缩伪影等具有鲁棒性。最近的一些作品试图使用生成对抗网络(GAN)从真实图像的数据集对这些退化进行建模。他们生成合成退化的LR图像,并使用它们与相应的真实高分辨率(HR)图像训练一个超分辨率(SR)网络使用的像素级损失和对抗性损失的组合。在本文中,我们提出了一个两个模块的超分辨率网络,其中特征提取器模块从LR图像中提取鲁棒特征,SR模块仅使用这些鲁棒特征生成HR估计。我们训练退化GAN将双三次下采样的干净图像转换为真正的退化图像,并在所获得的退化LR图像和其干净LR对应图像之间进行插值。然后,将该插值LR图像与其对应的HR对应物一起用于从端到端训练超分辨率网络。熵正则化Wasserstein散度用于强制从干净和退化图像中学习的编码特征与从插值图像中提取的编码特征非常相似,以确保鲁棒性。

英文摘要:

Real low-resolution (LR) face images contain degradations which are too varied and complex to be captured by known downsampling kernels and signal-independent noises. So, in order to successfully super-resolve real faces, a method needs to be robust to a wide range of noise, blur, compression artifacts etc. Some of the recent works attempt to model these degradations from a dataset of real images using a Generative Adversarial Network (GAN). They generate synthetically degraded LR images and use them with corresponding real high-resolution(HR) image to train a super-resolution (SR) network using a combination of a pixel-wise loss and an adversarial loss. In this paper, we propose a two module super-resolution network where the feature extractor module extracts robust features from the LR image, and the SR module generates an HR estimate using only these robust features. We train a degradation GAN to convert bicubically downsampled clean images to real degraded images, and interpolate between the obtained degraded LR image and its clean LR counterpart. This interpolated LR image is then used along with it's corresponding HR counterpart to train the super-resolution network from end to end. Entropy Regularized Wasserstein Divergence is used to force the encoded features learnt from the clean and degraded images to closely resemble those extracted from the interpolated image to ensure robustness.

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。

↑