Unsupervised Learning of Stereo Matching
Unsupervised Learning of Stereo Matching
复制标题
DOI：
10.1109/iccv.2017.174
复制
发表时间：
2017-10
期刊：
影响因子：
--
通讯作者：
Chao Zhou;Hong Zhang;Xiaoyong Shen;Jiaya Jia
中科院分区：
文献类型：
--
作者：
Chao Zhou;Hong Zhang;Xiaoyong Shen;Jiaya Jia
卷积神经网络在立体匹配代价学习方面展现出了能力。近期的方法从具有真实视差图的公开数据集中学习参数。由于标注真实深度存在困难，可用于系统训练的数据相当有限，这使得将该系统应用于实际应用变得困难。在本文中，我们提出了一种在无人工监督的情况下学习立体匹配代价的框架。我们的方法以迭代的方式更新网络参数。它从一个随机初始化的网络开始。采用左右一致性检查来指导训练。然后挑选出合适的匹配，并在后续迭代中用作训练数据。我们的系统最终收敛到一个稳定状态，其性能甚至与其他有监督的方法相当。
Convolutional neural networks showed the ability in stereo matching cost learning. Recent approaches learned parameters from public datasets that have ground truth disparity maps. Due to the difficulty of labeling ground truth depth, usable data for system training is rather limited, making it difficult to apply the system to real applications. In this paper, we present a framework for learning stereo matching costs without human supervision. Our method updates network parameters in an iterative manner. It starts with a randomly initialized network. Left-right check is adopted to guide the training. Suitable matching is then picked and used as training data in following iterations. Our system finally converges to a stable state and performs even comparably with other supervised methods.