Bayesian Structure-Preserving Image Contrast Enhancement and Its Simplification

Abstract

In this paper, an efficient Bayesian framework is proposed for image contrast enhancement. Based on the image acquisition pipeline, we model the image enhancement problem as a maximum a posteriori (MAP) estimation problem, where the posteriori probability is formulated based on the local information of the given image. In our framework, we express the likelihood model as a local image structure preserving constraint, where the overall effect of the shutter speed and camera response function is approximated as a linear transformation. On the other hand, we design the prior model based on the observed image and some statistical property of natural images. With the proposed framework, we can effectively enhance the contrast of the image in a natural-looking way, while with fewer artifacts at the same time. Moreover, in order to apply the proposed MAP formulation to typical enhancement problems, like image editing, we further convert the estimation process into an intensity mapping process, which can achieve comparable enhancement performance with a much lower computational complexity. Simulation results have demonstrated the feasibility of the proposed framework in providing flexible and effective contrast enhancement.