TY - JOUR
T1 - MGAN-CRCM
T2 - a novel multiple generative adversarial network and coarse refinement-based cognizant method for image inpainting
AU - Asad, Nafiz Al
AU - Pranto, Md Appel Mahmud
AU - Shiam, Shbiruzzaman
AU - Akand, Musaddeq Mahmud
AU - Yousuf, Mohammad Abu
AU - Hasan, Khondokar Fida
AU - Moni, Mohammad Ali
N1 - Publisher Copyright:
© The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.
PY - 2025
Y1 - 2025
N2 - Image inpainting is a recognized method for restoring the properties of pixels in damaged or incomplete images in computer vision technology. Some recent techniques based on generative adversarial network (GAN) image inpainting have outperformed traditional approaches due to their excellent deep learning capability and adaptability to various image domains. Since residual networks (ResNet) also gained popularity over time due to their property as a generative model, offering better feature representation and compatibility with other architectures, how could we leverage both of these models to result in even greater success in image inpainting? This paper proposes a novel architecture for image inpainting based on GAN and residual networks. Our proposed architecture consists of three models: Transpose Convolution-based GAN, Fast ResNet-Convolutional Neural Network, and Co-Modulation GAN. Transpose Convolution-based GAN is our newly designed architecture. It produces guided and blind image inpainting, and FR-CNN performs the object removal case. Co-Mod GAN acts as a refinement layer because it refines the results from Transpose Convolution-based GAN and FR-CNN. To train and evaluate our proposed architecture on publicly available benchmark datasets: CelebA, Places2, and ImageNet are used. Our approach proves our hypothesis, and our proposed model acquires the highest accuracy of 96.59% in the ImageNet dataset, FR-CNN acquires the highest accuracy of 96.70% in the Places2 dataset, and Co-Mod GAN acquires the highest accuracy of 96.16% in the CelebA dataset. Through an analysis of both qualitative and quantitative comparisons, it is evident that our proposed model exceeds existing architectures in performance.
AB - Image inpainting is a recognized method for restoring the properties of pixels in damaged or incomplete images in computer vision technology. Some recent techniques based on generative adversarial network (GAN) image inpainting have outperformed traditional approaches due to their excellent deep learning capability and adaptability to various image domains. Since residual networks (ResNet) also gained popularity over time due to their property as a generative model, offering better feature representation and compatibility with other architectures, how could we leverage both of these models to result in even greater success in image inpainting? This paper proposes a novel architecture for image inpainting based on GAN and residual networks. Our proposed architecture consists of three models: Transpose Convolution-based GAN, Fast ResNet-Convolutional Neural Network, and Co-Modulation GAN. Transpose Convolution-based GAN is our newly designed architecture. It produces guided and blind image inpainting, and FR-CNN performs the object removal case. Co-Mod GAN acts as a refinement layer because it refines the results from Transpose Convolution-based GAN and FR-CNN. To train and evaluate our proposed architecture on publicly available benchmark datasets: CelebA, Places2, and ImageNet are used. Our approach proves our hypothesis, and our proposed model acquires the highest accuracy of 96.59% in the ImageNet dataset, FR-CNN acquires the highest accuracy of 96.70% in the Places2 dataset, and Co-Mod GAN acquires the highest accuracy of 96.16% in the CelebA dataset. Through an analysis of both qualitative and quantitative comparisons, it is evident that our proposed model exceeds existing architectures in performance.
KW - Coarse refinement
KW - Deep learning
KW - Generative adversarial network (GAN)
KW - Image inpainting
KW - Image restoration
KW - Residual networks (ResNet)
UR - https://rdcu.be/d52Kp
UR - http://www.scopus.com/inward/record.url?scp=85214031644&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85214031644&partnerID=8YFLogxK
U2 - 10.1007/s00521-024-10886-9
DO - 10.1007/s00521-024-10886-9
M3 - Article
AN - SCOPUS:85214031644
SN - 0941-0643
JO - Neural Computing and Applications
JF - Neural Computing and Applications
M1 - 106789
ER -