DeepGIN: Deep Generative Inpainting Network for Extreme Image Inpainting
It addresses the challenge of generating visually pleasing inpainting results for diverse missing patterns in images, which is an incremental improvement over existing methods.
The paper tackled the problem of image inpainting for various types and sizes of missing parts, proposing DeepGIN which outperformed state-of-the-art methods on datasets like FFHQ and Oxford Buildings with improved quantitative and qualitative results.
The degree of difficulty in image inpainting depends on the types and sizes of the missing parts. Existing image inpainting approaches usually encounter difficulties in completing the missing parts in the wild with pleasing visual and contextual results as they are trained for either dealing with one specific type of missing patterns (mask) or unilaterally assuming the shapes and/or sizes of the masked areas. We propose a deep generative inpainting network, named DeepGIN, to handle various types of masked images. We design a Spatial Pyramid Dilation (SPD) ResNet block to enable the use of distant features for reconstruction. We also employ Multi-Scale Self-Attention (MSSA) mechanism and Back Projection (BP) technique to enhance our inpainting results. Our DeepGIN outperforms the state-of-the-art approaches generally, including two publicly available datasets (FFHQ and Oxford Buildings), both quantitatively and qualitatively. We also demonstrate that our model is capable of completing masked images in the wild.