Semi-parametric Image Inpainting
This addresses the problem of generating realistic image completions for irregular missing regions, which is important for applications like photo editing, but the approach is incremental as it builds on existing inpainting methods.
The paper tackled image inpainting for irregular holes by introducing a semi-parametric method that uses an external database to retrieve similar images as auxiliary information, achieving more realistic results than previous approaches as confirmed by a user study.
This paper introduces a semi-parametric approach to image inpainting for irregular holes. The nonparametric part consists of an external image database. During test time database is used to retrieve a supplementary image, similar to the input masked picture, and utilize it as auxiliary information for the deep neural network. Further, we propose a novel method of generating masks with irregular holes and present public dataset with such masks. Experiments on CelebA-HQ dataset show that our semi-parametric method yields more realistic results than previous approaches, which is confirmed by the user study.