Description

Inpainting is derived from art restoration, also called re-touching. Image Inpainting refers to the application of sophisticated algorithms to replace lost or corrupted parts of the image data. The main aim of inpainting is to fill scratches in the image or photos as well as to remove larger objects from them. The main objective of inpainting is to reconstruct the missing region in such a way that the observer does not comes to know that the image has been manipulated. Image inpainting has made remarkable progress with recent advances in deep learning. Popular networks mainly follow an encoder-decoder architecture and possess sufficiently large receptive field, i.e., larger than the image resolution. We propose the use of Local and Global Refinement Network, where the convolution is masked and renormalized to be conditioned on only valid pixels. We further include a mechanism to automatically generate an updated mask for the next layer as part of the forward pass. Our model outperforms other methods for irregular masks. We show qualitative and quantitative comparisons with other methods to validate our approach.