Globally optimized multiview video color correction using dense spatio-temporal matching

Multiview video is becoming increasingly popular as the format for 3D video systems that use autostereoscopic displays or freeviewpoint navigation capabilities. However, the algorithms that drive these applications are not yet mature and can suffer from subtle irregularities such as color imbalances inbetween different cameras. Regarding the problem of color correction, state-of-the-art methods directly apply some form of histogram matching in blocks of pixels between an input frame and a target frame containing the desired color distribution. These methods, however, typically suffer from artifacts in the gradient domain, as they do not take into account local texture information. This paper presents a novel method to correct color differences in multiview video sequences that uses a dense matching-based global optimization framework. The proposed energy function ensures preservation of local structures by regulating deviations from the original image gradients.