Survey on Semantic Stereo Matching / Semantic Depth Estimation

TL;DR

This survey reviews recent advances in semantic stereo matching, highlighting how semantic cues improve depth estimation, and compares state-of-the-art neural networks in accuracy and speed for real-time use.

Contribution

It provides a comprehensive comparison of recent neural network architectures for semantic stereo matching, emphasizing their performance in accuracy and speed.

Findings

Semantic cues enhance stereo matching accuracy.

Deep neural networks vary in speed and precision.

Current methods aim for real-time applications.

Abstract

Stereo matching is one of the widely used techniques for inferring depth from stereo images owing to its robustness and speed. It has become one of the major topics of research since it finds its applications in autonomous driving, robotic navigation, 3D reconstruction, and many other fields. Finding pixel correspondences in non-textured, occluded and reflective areas is the major challenge in stereo matching. Recent developments have shown that semantic cues from image segmentation can be used to improve the results of stereo matching. Many deep neural network architectures have been proposed to leverage the advantages of semantic segmentation in stereo matching. This paper aims to give a comparison among the state of art networks both in terms of accuracy and in terms of speed which are of higher importance in real-time applications.