融合GAN与残差网络，提升图像修复精度与细节还原能力。
MGAN-CRCM: A Novel Multiple Generative Adversarial Network and Coarse-Refinement Based Cognizant Method for Image Inpainting
- 设计三模块协同架构：生成对抗网络+快速残差卷积+联合调制机制
- 在ImageNet、Places2、CelebA上分别达到96.59%、96.70%、96.16%准确率
- 适合需要高保真修复的图像编辑与医学影像重建场景
图像修复是计算机视觉中用于重建图像缺失或损坏像素的常用技术。近年来，生成对抗网络（GAN）凭借深度学习能力与跨域适应性，在性能上超越传统方法。残差网络（ResNet）也因增强特征表达与架构兼容性而受到重视。本文提出一种结合GAN与ResNet的新架构，以改善图像修复效果。框架包含三个组件：基于转置卷积的GAN用于引导与盲修复，快速残差卷积神经网络（FR-CNN）用于物体移除，以及联合调制GAN（Co-Mod GAN）用于细节优化。模型在基准数据集上评估，于ImageNet、Places2、CelebA上分别取得96.59%、96.70%、96.16%的准确率。对比分析表明，该架构在定性与定量评价中均优于现有方法，验证了其有效性。
原文摘要 · Abstract (English)
Image inpainting is a widely used technique in computer vision for reconstructing missing or damaged pixels in images. Recent advancements with Generative Adversarial Networks (GANs) have demonstrated superior performance over traditional methods due to their deep learning capabilities and adaptability across diverse image domains. Residual Networks (ResNet) have also gained prominence for their ability to enhance feature representation and compatibility with other architectures. This paper introduces a novel architecture combining GAN and ResNet models to improve image inpainting outcomes. Our framework integrates three components: Transpose Convolution-based GAN for guided and blind inpainting, Fast ResNet-Convolutional Neural Network (FR-CNN) for object removal, and Co-Modulation GAN (Co-Mod GAN) for refinement. The model's performance was evaluated on benchmark datasets, achieving accuracies of 96.59% on Image-Net, 96.70% on Places2, and 96.16% on CelebA. Comparative analyses demonstrate that the proposed architecture outperforms existing methods, highlighting its effectiveness in both qualitative and quantitative evaluations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。