论文标题
多个基于示例的幻觉面对超分辨率和编辑
Multiple Exemplars-based Hallucinationfor Face Super-resolution and Editing
论文作者
论文摘要
鉴于面部的非常低分辨率的输入图像（例如16x16或8x8像素），本文的目的是重建其高分辨率版本。这本身就是一个问题不足的问题，因为低分辨率输入中缺少高频信息，并且需要根据图像内容的先验知识来幻觉。在本文中，我们不再依靠通用的面孔，而是探讨了一组示例的使用，即同一人的其他高分辨率图像。这些指导神经网络在我们调节其上的输出时。多个示例比单个示例更好。为了有效地结合来自多个示例的信息，我们引入了一个像素重量生成模块。除了标准面部超分辨率外，我们的方法还允许仅通过用另一个带有不同面部特征的套装代替示例来执行微妙的脸部编辑。进行了用户研究，并表明几乎无法将超级分辨图像与Celeba数据集上的真实图像区分开。定性比较表明，我们的模型优于Celeba和WebFace数据集文献中提出的方法。
Given a really low-resolution input image of a face (say 16x16 or 8x8 pixels), the goal of this paper is to reconstruct a high-resolution version thereof. This, by itself, is an ill-posed problem, as the high-frequency information is missing in the low-resolution input and needs to be hallucinated, based on prior knowledge about the image content. Rather than relying on a generic face prior, in this paper, we explore the use of a set of exemplars, i.e. other high-resolution images of the same person. These guide the neural network as we condition the output on them. Multiple exemplars work better than a single one. To combine the information from multiple exemplars effectively, we introduce a pixel-wise weight generation module. Besides standard face super-resolution, our method allows to perform subtle face editing simply by replacing the exemplars with another set with different facial features. A user study is conducted and shows the super-resolved images can hardly be distinguished from real images on the CelebA dataset. A qualitative comparison indicates our model outperforms methods proposed in the literature on the CelebA and WebFace dataset.
