Recently, deep learning-based techniques have shown great power in image inpainting especially dealing with squared holes. However, they fail to generate plausible results inside the missing regions for irregular and large holes as there is a lack of understanding between missing regions and existing counterparts. To overcome this limitation, we combine two non-local mechanisms including a contextual attention module (CAM) and an implicit diversified Markov random fields (ID-MRF) loss with a multi-scale architecture which uses several dense fusion blocks (DFB) based on the dense combination of dilated convolution to guide the generative network to restore discontinuous and continuous large masked areas. To prevent color discrepancies and grid-like artifacts, we apply the ID-MRF loss to improve the visual appearance by comparing similarities of long-distance feature patches. To further capture the long-term relationship of different regions in large missing regions, we introduce the CAM. Although CAM has the ability to create plausible results via reconstructing refined features, it depends on initial predicted results. Hence, we employ the DFB to obtain larger and more effective receptive fields, which benefits to predict more precise and fine-grained information for CAM. Extensive experiments on two widely-used datasets demonstrate that our proposed framework significantly outperforms the state-of-the-art approaches both in quantity and quality.

中文翻译：

---

局部和多尺度图像修复机制

最近，基于深度学习的技术在图像修复（尤其是处理方孔）中显示出强大的功能。但是，由于缺少区域和现有对应区域之间的理解，因此它们无法在不规则区域和较大孔的缺失区域内部产生合理的结果。为克服此限制，我们结合了两种非局部机制，包括上下文关注模块（CAM）和隐式多样化马尔可夫随机字段（ID-MRF）丢失，以及使用了基于多个密集融合块（DFB）的多尺度体系结构扩张卷积的密集组合来引导生成网络，以恢复不连续和连续的大蒙版区域。为防止颜色差异和类似网格的伪影，我们通过比较长距离特征块的相似性，应用ID-MRF损失来改善视觉外观。为了进一步捕获缺失大区域中不同区域的长期关系，我们引入了CAM。尽管CAM可以通过重建精细特征来创建合理的结果，但它取决于初始的预测结果。因此，我们使用DFB来获得更大，更有效的接收场，这有助于预测CAM的更精确和更细粒度的信息。在两个广泛使用的数据集上进行的大量实验表明，我们提出的框架在数量和质量上均显着优于最新方法。尽管CAM可以通过重建精细特征来创建合理的结果，但它取决于初始的预测结果。因此，我们使用DFB来获得更大，更有效的接收场，这有助于预测CAM的更精确和更细粒度的信息。在两个广泛使用的数据集上进行的大量实验表明，我们提出的框架在数量和质量上均显着优于最新方法。尽管CAM可以通过重建精细特征来创建合理的结果，但它取决于初始的预测结果。因此，我们使用DFB来获得更大，更有效的接收场，这有助于预测CAM的更精确和更细粒度的信息。在两个广泛使用的数据集上进行的大量实验表明，我们提出的框架在数量和质量上均显着优于最新方法。