Deep neural networks have shown great success in stereo matching in recent years. On the KITTI datasets, most top performing methods are based on neural networks. However, on the Middlebury datasets, these methods usually do not perform well. The KITTI datasets are collected in outdoor scenes while the Middlebury datasets are collected in indoor scenes. It is commonly believed that the community still lacks a large labelled dataset for stereo matching in indoor scenes. In this paper, we introduce a new stereo dataset called InStereo2K. It contains 2050 pairs of stereo images with highly accurate groundtruth disparity maps, including 2000 pairs for training and 50 pairs for test. Experimental results show that our dataset can significantly improve the performance of several latest networks (including StereoNet and PSMNet) on the Middlebury 2014 dataset. The large scale, high accuracy and rich diversity of the proposed InStereo2K dataset provide new opportunities to researchers in the area of stereo matching and beyond. It also takes end-to-end stereo matching methods a step towards practical applications.

近年来，深度神经网络在立体声匹配方面已显示出巨大的成功。在KITTI数据集上，大多数性能最高的方法都是基于神经网络的。但是，在Middlebury数据集上，这些方法通常效果不佳。KITTI数据集收集在室外场景中，而Middlebury数据集收集在室内场景中。通常认为，社区仍然缺乏用于室内场景中立体声匹配的大标签数据集。在本文中，我们介绍了一个称为InStereo2K的新立体声数据集。它包含2050对立体图像和高度准确的地面真实视差图，包括用于训练的2000对和用于测试的50对。实验结果表明，我们的数据集可以显着改善Middlebury 2014数据集上几个最新网络（包括StereoNet和PSMNet）的性能。所提出的InStereo2K数据集的大规模，高精度和丰富多样性为立体声匹配及其他领域的研究人员提供了新的机会。它还将端到端立体声匹配方法迈向了实际应用。