MGAN-CRCM: A Novel Multiple Generative Adversarial Network and Coarse-Refinement Based Cognizant Method for Image Inpainting

TL;DR

This paper presents MGAN-CRCM, an innovative image inpainting framework combining multiple GANs and ResNet components, achieving state-of-the-art results on benchmark datasets through a coarse-refinement process.

Contribution

It introduces a novel architecture integrating GAN, ResNet, and refinement modules for improved image inpainting performance.

Findings

Achieved over 96% accuracy on Image-Net, Places2, and CelebA datasets.

Outperforms existing inpainting methods in qualitative and quantitative evaluations.

Demonstrates effectiveness of combined GAN and ResNet architecture for diverse inpainting tasks.

Abstract

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.