English

Exploring Stereovision-Based 3-D Scene Reconstruction for Augmented Reality

Computer Vision and Pattern Recognition 2019-02-19 v1

Abstract

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.

Keywords

Cite

@article{arxiv.1902.06255,
  title  = {Exploring Stereovision-Based 3-D Scene Reconstruction for Augmented Reality},
  author = {Guang-Yu Nie and Yun Liu and Cong Wang and Yue Liu and Yongtian Wang},
  journal= {arXiv preprint arXiv:1902.06255},
  year   = {2019}
}

Comments

To be published in IEEE VR2019 Conference as a Poster

R2 v1 2026-06-23T07:42:58.789Z