New Color Correction Approach to Multi-view Images with Region Correspondence

摘要

Color appearance of the same object between different viewpoints may be different due to inconsistent illumination or inevitable errors and noises resulting from imaging devices, which brings difficulties to the subsequent multi-view image compression and arbitrary viewpoint rendering. Thus, color correction is necessary for multi-view applications. In this paper, a color correction method of multi-view images is proposed based on region correspondence. Through expectation-maximum segmentation for reference image and current viewpoint image, mapping relationship is built with similar statistical model between two regions in the two images. Experimental results show that the proposed method can be used to correct the color of viewpoint images according to the color of the reference image, and preserve the visual impression of the viewpoint images simultaneously.