Abstract
To solve the issue that it is difficult to maintain the consistency of linear structures when filling large regions by the exemplar-based technique, a hierarchical guidance strategy and exemplar-based image inpainting technique is proposed. The inpainting process is as follows: (i) the multi-layer resolution images are firstly acquired through decomposing of the pyramid on the target image; (ii) the top-layer inpainted image, the beginning of the inpainting from the top layer, is generated by the exemplar-based technique; (iii) there is a combined result between the next layer of the top image and the up-sampling output on the top-layer inpainted image, and the target regions are filled with information as guidance data; (iv) this process is repeated until the inpainting of all layers have been completed. Our results were compared to those obtained by existing techniques, and our proposed technique maintained the consistency of linear structures in a visually plausible way. Objectively, we choose SSIM (structural similarity index measurement) and PSNR (peak signal-to-noise ratio) as the measurement indices. Since the values of SSIM are well reflected when compared with other techniques, our technique clearly demonstrated that our approach is better able to maintain the consistency of linear structures. The core of our algorithm is to fill large regions whether they are synthesis images or real-scene photographs. It is easy to apply in practice, with the goal of having plausible inpainted image.
Highlights
Image inpainting belongs to the field of image retouching; users who do not see the original image accept the inpainting result on conditon that the restored image maintains visual consistency
Since image inpainting was proposed by Bertalmio et al [1], many scholars have begun to study image inpainting in recent years, and the representative inpainting approaches fall into two classes: The former is the technique based on variational partial differential
Has two advantages of simultaneous filling texture and structure. Combining these two classes of techniques, we propose an exemplar-based technique and hierarchical guidance strategy inpainting algorithm in this paper
Summary
Image inpainting belongs to the field of image retouching; users who do not see the original image accept the inpainting result on conditon that the restored image maintains visual consistency. The typical methods proposed by Chan et al [2,3,4] are the TV model, the curvature-driven model, and Euler’s elastica model, which efficiently fill small image regions but fill texture images poorly. The latter class is the exemplar-based technique proposed by Criminisi et al [5], which has the advantages of simultaneously. After decomposing the pyramid in the original image, the target regions of the top layer are filled by the exemplar-based technique. The sum image contained information located in the target regions, which is considered as the guidance information when inpainting the layer by the exemplar-based technique. Compared to the results obtained by single inpainting, the proposed method in the paper can remarkably improve the effectiveness of inpainting
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
