Exploring Stereovision-Based 3-D Scene Reconstruction for Augmented Reality
This work addresses scene reconstruction for augmented reality applications, but it appears incremental as it modifies an existing network.
The paper tackled 3-D scene reconstruction for augmented reality by proposing SLED-Net, an improved stereo matching network that outperformed state-of-the-art methods on Scene Flow and KITTI2015 datasets.
Three-dimensional (3-D) scene reconstruction is one of the key techniques in Augmented Reality (AR), which is related to the integration of image processing and display systems of complex information. Stereo matching is a computer vision based approach for 3-D scene reconstruction. In this paper, we explore an improved stereo matching network, SLED-Net, in which a Single Long Encoder-Decoder is proposed to replace the stacked hourglass network in PSM-Net for better contextual information learning. We compare SLED-Net to state-of-the-art methods recently published, and demonstrate its superior performance on Scene Flow and KITTI2015 test sets.