TL;DR
This paper introduces a two-stage high-resolution image inpainting method that enhances texture restoration and resolution independence, enabling effective filling of arbitrary-size images without retraining existing models.
Contribution
It proposes a novel approach that improves texture restoration and resolution flexibility in image inpainting, compatible with existing models and usable via a GIMP plugin.
Findings
Enables inpainting of arbitrary-size images.
Improves texture fragment restoration.
Works with existing inpainting models without retraining.
Abstract
In recent years, the field of image inpainting has developed rapidly, learning based approaches show impressive results in the task of filling missing parts in an image. But most deep methods are strongly tied to the resolution of the images on which they were trained. A slight resolution increase leads to serious artifacts and unsatisfactory filling quality. These methods are therefore unsuitable for interactive image processing. In this article, we propose a method that solves the problem of inpainting arbitrary-size images. We also describe a way to better restore texture fragments in the filled area. For this, we propose to use information from neighboring pixels by shifting the original image in four directions. Moreover, this approach can work with existing inpainting models, making them almost resolution independent without the need for retraining. We also created a GIMP plugin…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsInpainting
