Stereo-Matching Network for Structured Light

Abstract

Recently, deep learning has been widely applied in binocular stereo matching for depth acquisition, which has led to an immense increase of accuracy. However, little attention has been paid to the structured light field. In this letter, a network for structured light is proposed to extract effective matching features for depth acquisition. The proposed network promotes the Siamese network by considering receptive fields of different scales and assigning proper weights to the corresponding features, which is achieved by combining pyramid-pooling structure with the squeeze-and-excitation network into the Siamese network for feature extraction and weight calculations, respectively. For network training and testing, a structured-light dataset with amended ground truths is generated by projecting a random pattern into the existing binocular stereo dataset. Experiments demonstrate that the proposed network is capable of real-time depth acquisition, and it provides superior depth maps using structured light.