【摘要】 为了修复大面积破损图像，提出了一种新的多重修复网络模型。首先该模型通过增加特征修复环节减少了修复错误在网络上采样过程中的积累；其次提出多尺度修复模块(MSRM),该模块能够综合不同视野的信息对特征图进行补全；然后利用注意力机制对修复块进行优化，解决了由不同区域修复程度不同导致的输出图像各区域色彩不协调问题；最后对损失函数进行改进，使模型更加注重对图像破损区域的修复。实验结果显示，在Places2和CelebA数据集上的修复图像的质量均有不同程度的提升，并且随着图像缺失像素比例增大，提升效果更加明显。更多还原

【Abstract】 To restore images with large damaged areas, this paper proposes a new multi-stage inpainting network model. Firstly, the model reduces the accumulation of inpainting errors during the upsampling process by extending the feature inpainting procedure. Secondly, the multi-scale restoration module(MSRM) is proposed, which can synthesize the information from different receptive fields to complete the feature map. Thirdly, an attention mechanism is employed to optimize the inpainting process, resolving the issue of color inconsistency in the output image caused by non-uniform restoration across different regions. Finally, the loss function is improved to make the model focus more on repair-ing the damaged regions. Experimental results show that the quality of the restored images of the model on both Places2 and CelebA datasets is improved to different degrees, and the improvement effect is more obvious as the proportion of missing pixels in the image increases.更多还原