A Precise-Mask-Based Method for Enhanced Image Inpainting

Abstract EN

Mask of damage region is the pretreatment step of the image inpainting, which plays a key role in the ultimate effect.

However, state-of-the-art methods have attached significance to the inpainting model, and the mask of damage region is usually selected manually or by the conventional threshold-based method.

Since manual method is time-consuming and the threshold-based method does not have the same precision for different images, we herein report a new method for automatically constructing the precise mask by the joint filtering of guided filtering and L 0 smoothing.

It can accurately locate the boundary of damaged region in order to effectively segment the damage region and then greatly improves the ultimate effect of image inpainting.

The experimental results show that the proposed method is superior to state-of-the-art methods in the step of constructing inpainting mask, especially for the damaged region with inconspicuous boundary.