Deep Blind Image Inpainting
This addresses the problem of restoring images with unknown corruptions for applications like photo editing, though it is incremental as it builds on residual learning.
The paper tackles blind image inpainting, where corrupted regions are unknown, by proposing an encoder-decoder architecture with a robust loss function to restore clear images, achieving favorable performance against state-of-the-art methods in handling arbitrary-shaped corruptions.
Image inpainting is a challenging problem as it needs to fill the information of the corrupted regions. Most of the existing inpainting algorithms assume that the positions of the corrupted regions are known. Different from the existing methods that usually make some assumptions on the corrupted regions, we present an efficient blind image inpainting algorithm to directly restore a clear image from a corrupted input. Our algorithm is motivated by the residual learning algorithm which aims to learn the missing infor- mation in corrupted regions. However, directly using exist- ing residual learning algorithms in image restoration does not well solve this problem as little information is available in the corrupted regions. To solve this problem, we introduce an encoder and decoder architecture to capture more useful information and develop a robust loss function to deal with outliers. Our algorithm can predict the missing information in the corrupted regions, thus facilitating the clear image restoration. Both qualitative and quantitative experimental demonstrate that our algorithm can deal with the corrupted regions of arbitrary shapes and performs favorably against state-of-the-art methods.