Feature-Based Color Correction of Multiview Video for Coding and Rendering Enhancement

Abstract

Multi-View Video (MVV) consists of capturing the same scene with multiple cameras from different viewpoints. Therefore, substantial illumination and color inconsistencies can be observed between the different views. These color mismatches can reduce significantly compression efficiency and rendering quality. In this paper, we propose a preprocessing method for cor- recting these color discrepancies in MVV. To consider occlusion problem, our method is based on an improvement of Histogram Matching (HM) algorithm using only common regions across views. These regions are defined by an invariant feature detector (SIFT), followed by RANSAC algorithm to increase the matching robustness. In addition, to maintain temporal correlation, HM algorithm is applied on a temporal sliding-window, allowing to cope with time-varying acquiring system, camera moving capture and real-time broadcasting. Moreover, unlike to choose always by default the center view as the reference one, we propose an automatic selection algorithm based on both views statistics and quality. Experimental results show that the proposed method increases coding efficiency with gains of up to 1.1 dB and 2.2 dB for the luminance and chrominance components, respectively. Further, once the correction is performed, the color of real and rendered views is harmonized and looks very consistent as a whole.