摘要：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.
