Hybrid plane fitting for depth estimation

In this paper, a novel plane fitting algorithm with low complexity and high accuracy is proposed to refine the depth maps generated by stereo matching. We first compute the confidence coefficient for each pixel in the depth map by cross checking and stable pixel calculation. According to the outlier pixel percentage for each segment, we choose one method, either proposed weighted least square error based or RANSAC based plane fitting algorithm, to estimate the plane parameters. Experimental results show that our method outperforms other existing plane fitting algorithms.