Low Complexity Image Inpainting Using AutoEncoder

Image inpainting is filling the missing or corrupted pixels in an image in a realistic way that cannot be differentiated by human eye. Deep learning is widely used in image inpainting and it exhibits better performance than classical inpainting methods, but it requires high processing resources and longer time to train the model. In this paper, we propose an autoencoder architecture that outperforms other deep learning techniques in literature methods with lower processing and time complexity.