论文标题
Deepgin：用于极端图像插入的深层生成的镶嵌网络
DeepGIN: Deep Generative Inpainting Network for Extreme Image Inpainting
论文作者
论文摘要
图像插入的难度程度取决于缺失部分的类型和大小。现有的图像介入方法通常会遇到困难在完成野外缺失的零件，并具有令人愉悦的视觉和上下文结果，因为它们接受了处理一种特定类型的缺失模式（蒙版）或单方面假设掩盖区域的形状和/或尺寸的培训。我们提出了一个名为Deepgin的深层生成的镶嵌网络，以处理各种类型的掩盖图像。我们设计了空间金字塔扩张（SPD）重新网络块，以实现远处的特征进行重建。我们还采用了多尺度的自我注意力（MSSA）机制和返回投影（BP）技术来增强我们的介入结果。我们的Deepgin的表现通常超过了最先进的方法，包括两个公开可用的数据集（FFHQ和牛津建筑），无论是定量还是质量上）。我们还证明了我们的模型能够在野外完成蒙版的图像。
The degree of difficulty in image inpainting depends on the types and sizes of the missing parts. Existing image inpainting approaches usually encounter difficulties in completing the missing parts in the wild with pleasing visual and contextual results as they are trained for either dealing with one specific type of missing patterns (mask) or unilaterally assuming the shapes and/or sizes of the masked areas. We propose a deep generative inpainting network, named DeepGIN, to handle various types of masked images. We design a Spatial Pyramid Dilation (SPD) ResNet block to enable the use of distant features for reconstruction. We also employ Multi-Scale Self-Attention (MSSA) mechanism and Back Projection (BP) technique to enhance our inpainting results. Our DeepGIN outperforms the state-of-the-art approaches generally, including two publicly available datasets (FFHQ and Oxford Buildings), both quantitatively and qualitatively. We also demonstrate that our model is capable of completing masked images in the wild.
