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

## TL;DR

This paper introduces SLED-Net, an improved stereo matching network for 3-D scene reconstruction in AR, demonstrating superior performance over recent methods on standard datasets.

## Contribution

Proposes SLED-Net with a Single Long Encoder-Decoder to enhance contextual learning in stereo matching for AR applications.

## Key findings

- SLED-Net outperforms state-of-the-art methods on Scene Flow dataset.
- SLED-Net achieves better accuracy on KITTI2015 test set.
- The proposed network improves 3-D scene reconstruction quality.

## 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.