论文标题
边缘的发电机：面部图像的重建
Generator From Edges: Reconstruction of Facial Images
论文作者
论文摘要
涉及监督培训的应用需要配对的图像。单图像超分辨率（SISR）的研究人员通过人为地产生来自相应地面真理的模糊输入图像来创建此类图像。同样，我们可以创建具有Canny Edge的配对图像。我们从边缘（GFE）提出生成器[图2]。我们的目的是确定GFE的最佳体系结构，以及对感知损失的评论[1，2]。为此，我们进行了三个实验。首先，我们探讨了经常在SISR中使用的对抗性损失的影响。特别是，我们发现形成感知损失不是必不可少的组成部分。从硬件资源的角度来看，消除对抗性损失将导致更有效的体系结构。这也意味着，与生成对抗网络（GAN）[3]（例如模式崩溃）有关的问题是不需要的。其次，我们重新检查了VGG损失，发现中层产生了最佳效果。通过提取VGG损失的全部潜力，感知损失的总体表现可显着提高。第三，根据前两个实验的发现，我们重新评估了密集的网络以构建GFE。将GFE用作中间过程，从铅笔草图中重建面部图像可能会成为一项简单的任务。
Applications that involve supervised training require paired images. Researchers of single image super-resolution (SISR) create such images by artificially generating blurry input images from the corresponding ground truth. Similarly we can create paired images with the canny edge. We propose Generator From Edges (GFE) [Figure 2]. Our aim is to determine the best architecture for GFE, along with reviews of perceptual loss [1, 2]. To this end, we conducted three experiments. First, we explored the effects of the adversarial loss often used in SISR. In particular, we uncovered that it is not an essential component to form a perceptual loss. Eliminating adversarial loss will lead to a more effective architecture from the perspective of hardware resource. It also means that considerations for the problems pertaining to generative adversarial network (GAN) [3], such as mode collapse, are not necessary. Second, we reexamined VGG loss and found that the mid-layers yield the best results. By extracting the full potential of VGG loss, the overall performance of perceptual loss improves significantly. Third, based on the findings of the first two experiments, we reevaluated the dense network to construct GFE. Using GFE as an intermediate process, reconstructing a facial image from a pencil sketch can become an easy task.
