Authors - Aditya Ajitrao Kulkarni, Mayuri Shelke, Saurabh Babasaheb Gonte, Kalpak Sanjay Kedari, Parikshit Balasaheb Jadhav Abstract - Image inpainting is a basic problem in image restoration that focuses on recovering the missing or damaged areas of an image in a visually plausible and semantically consistent way. However, in practical image restoration tasks like historical photo restoration, images are often degraded by complex damages like cracks, scratches, fading, stains, and tone changes. Conventional image restoration methods relying on interpolation or diffusion have limitations in restoring high-frequency details and global semantic information. This paper presents a gated convolutional neural network with a U-Net structure for effective image inpainting and restoration with resolution enhancement. The proposed network is trained on a large-scale dataset of more than 20,000 synthetically degraded images created from the CelebA dataset, considering various damage patterns like scratches, cracks, random occlusions, blurring, grayscale conversion, and sepia tone transformation. The image restoration process involves two steps: context-aware image inpainting and resolution refinement. The proposed framework is extensively evaluated using PSNR and SSIM metrics for its effectiveness in color, grayscale, and sepia image restoration.
Open Zoom