Computing Curvature, Mean Curvature and Weighted Mean Curvature

CNNs? strong inductive biases of locality and weight sharing provide powerful representation ability and data sample utilization efficiency, which is very suitable for vision tasks. However, the weight sharing might smooth out the discrepancy between similar pixels, resulting in the wrong matching between left and right camera-image pair in thin structures region and repetitive texture region. in this paper, we propose a novel Heterogeneous Feature Fusion in MLP (HFF-MLP) for Stereo matching. It employs MLP structure and relaxes the weights sharing in the local spatial region. To this end, pixels in thin structures region and repetitive texture region are dealt with independently using the exclusive weights, and special information of these pixels are retained for accurate matching. Based on our proposed HFF -MLP module, we design a real-time network, i.e., MLP-Stereo. Experimental results show that our proposed HFF-MLP achieves competitive results on KITTI 2015 test dataset with the running time of 46 milliseconds. Furthermore, it performs much better than other real-time network in thin structures region and repetitive texture region.