INPAINTING MISSING REGIONS IN IMAGES: MEDICAL AND PHOTOGRAPHIC INPAINTING USING DEEP LEARNING

This paper presented a deep learning based image inpainting framework for medical and photographic applications. The proposed GAN based system achieves high quality reconstruction and structural preservation.  Future work includes integrating diffusion based generative models for improved realism, incorporating transformer based architectures for global context modeling, developing anatomy constrained inpainting methods for clinical reliability, and optimizing models for edge device deployment.

·             Y. Chen et al., “Contextual Attention Based Image Inpainting Using Deep Generative Models,” IEEE Transactions on Image Processing, 2023.   ·             M. Kumar et al., “GAN Based Medical Image Restoration and Reconstruction,”  IEEE Transactions on Medical Imaging, 2024.   ·             L. Zhang et al., “Transformer Driven Image Inpainting with Global Context Modeling,” IEEE Transactions on Artificial Intelligence, 2024. ·             R. Patel et al., “Anatomy Aware Deep Inpainting for Clinical Imaging,” IEEE Transactions on Biomedical Engineering, 2025. ·        Singh et al., “Lightweight Generative Models for RealTime Image Inpainting,” IEEE Internet of Things Journal, 2026. ·        T. Nguyen et al., “Adversarial Learning for Visual Content Restoration,” IEEE Access, 2023. ·        P. Wang et al., “Perceptual Loss Optimization in Image Completion Tasks,” IEEE Transactions on Neural Networks and Learning Systems, 2024. ·        K. Roy et al., “Hybrid Spatial Attention Networks for Image Restoration,” IEEE Access, 2025.   ·        J. Brown et al., “Advanced Generative Architectures for Visual Content Reconstruction,” IEEE Access, 2026. ·        S. Verma et al., “Deep Learning Based Medical Image Enhancement Techniques,” IEEE Transactions on Artificial Intelligence, 2024. ·        D. Sharma et al., “Scalable Image Completion Frameworks Using Generative Models,” IEEE Access, 2025.