Fused Multiscale Cost Volume for Efficient Stereo Matching

Stereo matching is an important part of reconstructing depth information and 3D scenes. However, a important problem is improving accuracy and efficiency at the same time. We propose an end-to-end convolutional neural network model to estimate disparity from stereo images. To improve the accuracy of feature extraction in complex regions, we use atrous spatial pyramid pooling module to extract and fuse features, and atrous convolutions of different rates explicitly adjust the receptive field of the filter. To balance the accuracy of the algorithm and GPU memory consumption, we design a fused multiscale cost volume and the fusion strategy to improve the efficiency in estimating the disparity, which reduces the amount of memory consumption while ensuring the accuracy of the algorithm. Our model is trained and evaluated on SceneFlow and KITTI datasets. Experimental results demonstrate that our method achieve a better accuracy even in weak textures areas, while GPU memory consumption and runtime are reduced.