MGAN-CRCM: A Novel Multiple Generative Adversarial Network and Coarse-Refinement Based Cognizant Method for Image Inpainting
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910764421349376 |
|---|---|
| author | Asad, Nafiz Al Pranto, Md. Appel Mahmud Shiam, Shbiruzzaman Akand, Musaddeq Mahmud Yousuf, Mohammad Abu Hasan, Khondokar Fida Moni, Mohammad Ali |
| author_facet | Asad, Nafiz Al Pranto, Md. Appel Mahmud Shiam, Shbiruzzaman Akand, Musaddeq Mahmud Yousuf, Mohammad Abu Hasan, Khondokar Fida Moni, Mohammad Ali |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_19000 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MGAN-CRCM: A Novel Multiple Generative Adversarial Network and Coarse-Refinement Based Cognizant Method for Image Inpainting Asad, Nafiz Al Pranto, Md. Appel Mahmud Shiam, Shbiruzzaman Akand, Musaddeq Mahmud Yousuf, Mohammad Abu Hasan, Khondokar Fida Moni, Mohammad Ali Computer Vision and Pattern Recognition Machine Learning Image and Video Processing 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. |
| title | MGAN-CRCM: A Novel Multiple Generative Adversarial Network and Coarse-Refinement Based Cognizant Method for Image Inpainting |
| topic | Computer Vision and Pattern Recognition Machine Learning Image and Video Processing |
| url | https://arxiv.org/abs/2412.19000 |