INTENSITY-BASED AND GRADIENT-BASED STEREO MATCHING USING HIERARCHICALGAUSSIAN-BASIS FUNCTIONS

In this paper, we propose a stereo correspondence method by minimizing intensity and gradient errors simultaneously. In contrast to conventi onal use of image gradients, the gradients are applied in the deformed image space. Although a uniform smoothness constraint is imposed, it is applied only to nonfeature regions. To avoid local minima in the fu nction minimization, we propose to parameterize the disparity function by hierarchical Gaussians. Both the uniqueness and the ordering const raints can be easily imposed in our minimization framework. Besides, w e propose a method to estimate the disparity map and the camera respon se difference parameters simultaneously. Experiments with various real stereo images show robust performances of our algorithm.