| 主权项 |
1. A processor-implemented method for image inpainting, comprising:
aligning, via one or more hardware processors, a plurality of multi-view images of a scene with respect to a reference image to obtain a plurality of aligned multi-view images; selecting, via the one or more hardware processors, a region of interest (ROI) in the reference image, the ROI representing a region to be removed from the reference image for image inpainting, selecting the ROI in the reference image configuring a hole to be filled in the reference image; computing, via the one or more hardware processors, priority values associated with a plurality of pixels of the ROI, the priority value of a pixel of the plurality of pixels computed based on a product of a confidence term and a data term, the confidence term measuring an amount of reliable information surrounding the pixel and the data term encouraging synthesis of a linear combination of image-patches based on the priority value; creating, via the one or more hardware processors, a dictionary comprising a plurality of image-patches selected from the reference image, the plurality of aligned multi-view images, and image patches obtained by 3-Dimensional (3D) rotation of image-patches selected from the reference image and the plurality of aligned multi-view images; and systematically reconstructing, via the one or more hardware processors, the ROI in the reference image based at least on the priority values associated with the plurality of pixels and the dictionary by computing a linear combination of two or more image-patches selected from the plurality of image-patches of the dictionary. |
