L0 co-intrinsic images decomposition

In this paper, we focus on co-intrinsic decomposition, a new problem that performs intrinsic decomposition on a pair of images simultaneously, which share the same foreground with arbitrarily different illuminations and backgrounds. We specifically demand the common foreground across different images to share same reflectance values. For the purpose of efficiency and feasibility, we perform the co-intrinsic decomposition at superpixel-level and propose a uniform approach to automatically derive non-local reflectance relationships via unsupervised L₀ sparsity between superpixels from intra-and inter-images. We present a unicolor-light-based intrinsic model, from which we construct a non-local L₀ sparse co-Retinex model that imposes feasible constraints on shading, reflectance and environment light, respectively. The co-intrinsic decomposition is finally modeled as a quadratic minimization problem that leads to a fast closed form solution. Extensive experiments show plausible results of our approach in extracting common reflectance components from multiple images. We also validate the benefits of our results in boosting the accuracy of image co-saliency detection.