Matting-Based Residual Optimization for Structurally Consistent Image Color Correction

Abstract

Image color correction aims to eliminate color differences between images, especially for color consistency in panoramic or stereoscopic images. Nowadays, the global color correction methods cannot correct local color differences, while the local color correction methods usually lead to structural inconsistency between local regions and image clarity reduction. To address these problems, we propose a matting-based residual optimization for structurally consistent image color correction (MROC). Inspired by the residual image, we formulate the image color correction problem as the optimization of a residual image between the input target image and the resulting image. The residual image is initialized and improved by the soft matting method with a closed-form solution. Besides, a data term is introduced to identify those pixels with higher color and structural consistencies and preserve these pixels during optimization. The whole computational infrastructure operates at the pixel level to correct local color differences while maintaining image clarity. Experimental results demonstrate that the performance of the proposed MROC method is superior to the state-of-the-art image color correction methods. Furthermore, the proposed matting-based residual optimization can also be incorporated in a variety of color correction methods, with enhanced outcomes justified by a group of image quality assessment metrics.