TL;DR本文提出了一种利用扩张卷积密集组合,通过设计自主回归损失、几何对齐约束项和具有局部和全局分支的判别器等方法改进图像修复的 GAN 模型。实验表明,该方法在多个公共数据集上都优于现有的最先进方法。
Abstract
image inpainting techniques have shown promising improvement with the assistance of generative adversarial networks (GANs) recently. However, most of them often suffered from completed results with unreasonable s