论文标题
MAT：用于大孔图像介绍的面具感知的变压器
MAT: Mask-Aware Transformer for Large Hole Image Inpainting
论文作者
论文摘要
最近的研究表明，在介入问题中建模长距离相互作用的重要性。为了实现这一目标，现有方法利用独立的注意技术或变压器，但考虑到计算成本，通常在低分辨率下。在本文中，我们提出了一种基于变压器的新型模型，用于大孔介绍，该模型统一了变压器和卷积的优点，以有效地处理高分辨率图像。我们仔细设计框架的每个组件，以确保恢复图像的高忠诚度和多样性。具体而言，我们自定义了一个面向内部的变压器块，其中注意模块仅从部分有效令牌中汇总非本地信息，该信息由动态掩码表示。广泛的实验证明了在多个基准数据集上新模型的最新性能。代码在https://github.com/fenglinglwb/mat上发布。
Recent studies have shown the importance of modeling long-range interactions in the inpainting problem. To achieve this goal, existing approaches exploit either standalone attention techniques or transformers, but usually under a low resolution in consideration of computational cost. In this paper, we present a novel transformer-based model for large hole inpainting, which unifies the merits of transformers and convolutions to efficiently process high-resolution images. We carefully design each component of our framework to guarantee the high fidelity and diversity of recovered images. Specifically, we customize an inpainting-oriented transformer block, where the attention module aggregates non-local information only from partial valid tokens, indicated by a dynamic mask. Extensive experiments demonstrate the state-of-the-art performance of the new model on multiple benchmark datasets. Code is released at https://github.com/fenglinglwb/MAT.
