MxT: Mamba x Transformer for Image Inpainting（用于图像修复的Mamba与Transformer融合架构）
MxT: Mamba x Transformer for Image Inpainting
AI总结：
针对现有图像修复方法在全局上下文建模、计算效率和细粒度细节保留上的不足，本研究提出融合Mamba与Transformer的MxT架构，通过双层交互学习提升修复质量，在主流数据集上超越现有最优方法。
摘要：
图像修复（image inpainting，又称图像补全）是计算机视觉中的一项关键任务，旨在用语义连贯的内容恢复图像中缺失或受损的区域。该技术需要在局部纹理复制与全局上下文理解之间实现精准平衡，以确保修复后的图像与周围区域无缝融合。传统卷积神经网络（CNNs）方法虽能有效捕捉局部模式，但由于感受野有限，往往难以处理更广泛的上下文关联。近期研究引入了transformer，利用其理解全局交互的能力，但这类方法存在计算效率低下的问题，且难以保留细粒度细节。为解决这些挑战，我们提出了MxT架构，其核心为所设计的混合模块（Hybrid Module，HM），该模块以协同方式将Mamba与transformer相结合。Mamba擅长以线性计算成本高效处理长序列，是transformer处理长程数据交互的理想补充。我们的混合模块可在像素级和补丁级实现双层交互学习，极大提升了模型重建高质量、具备上下文准确性图像的能力。我们在广泛使用的CelebA-HQ和Places2-standard数据集上对MxT进行了评估，其性能始终优于现有最优方法。代码将发布于：https://github.com/ChrisChen1023/MxT。
英文摘要：
Image inpainting, or image completion, is a crucial task in computer vision that aims to restore missing or damaged regions of images with semantically coherent content. This technique requires a precise balance of local texture replication and global contextual understanding to ensure the restored image integrates seamlessly with its surroundings. Traditional methods using Convolutional Neural Networks (CNNs) are effective at capturing local patterns but often struggle with broader contextual relationships due to the limited receptive fields. Recent advancements have incorporated transformers, leveraging their ability to understand global interactions. However, these methods face computational inefficiencies and struggle to maintain fine-grained details. To overcome these challenges, we introduce MxT composed of the proposed Hybrid Module (HM), which combines Mamba with the transformer in a synergistic manner. Mamba is adept at efficiently processing long sequences with linear computational costs, making it an ideal complement to the transformer for handling long-scale data interactions. Our HM facilitates dual-level interaction learning at both pixel and patch levels, greatly enhancing the model to reconstruct images with high quality and contextual accuracy. We evaluate MxT on the widely-used CelebA-HQ and Places2-standard datasets, where it consistently outperformed existing state-of-the-art methods. The code will be released: {\url{https://github.com/ChrisChen1023/MxT}}.
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。
