图像修复增强：用输入图像的自注意力区域替换原始掩码
Image inpainting enhancement by replacing the original mask with a self-attended region from the input image
AI总结：
本文提出一种基于视觉Transformer的预处理方法，用自注意力区域替换掩码以增强图像修复性能，在四个数据集上优于四个标准模型。
摘要：
图像修复，即通过重建像素信息来恢复图像中缺失或损坏区域的过程，近年来通过基于深度学习的方法取得了显著进展。在本文中，我们提出了一种新颖的基于深度学习的图像修复预处理方法，利用视觉Transformer（ViT）。我们的方法涉及用ViT生成的像素值替换掩码像素值，利用注意力矩阵中的多样化视觉补丁来捕获判别性空间特征。据我们所知，这是首次为图像修复任务提出此类预处理模型。此外，我们展示了我们的方法可以有效地应用于预训练的ViT模型，并使用预定义的补丁大小。为了评估所提出方法的泛化能力，我们提供了实验结果，将我们的方法与四个标准模型在四个公共数据集上进行比较，证明了我们的预处理技术在增强修复性能方面的有效性。
英文摘要：
Image inpainting, the process of restoring missing or corrupted regions of an image by reconstructing pixel information, has recently seen considerable advancements through deep learning-based approaches. In this paper, we introduce a novel deep learning-based pre-processing methodology for image inpainting utilizing the Vision Transformer (ViT). Our approach involves replacing masked pixel values with those generated by the ViT, leveraging diverse visual patches within the attention matrix to capture discriminative spatial features. To the best of our knowledge, this is the first instance of such a pre-processing model being proposed for image inpainting tasks. Furthermore, we show that our methodology can be effectively applied using the pre-trained ViT model with pre-defined patch size. To evaluate the generalization capability of the proposed methodology, we provide experimental results comparing our approach with four standard models across four public datasets, demonstrating the efficacy of our pre-processing technique in enhancing inpainting performance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
