Survey on Semantic Stereo Matching / Semantic Depth Estimation
It addresses the challenge of pixel correspondences in non-textured, occluded, and reflective areas for applications like autonomous driving and robotics, but it is incremental as it focuses on comparing existing methods.
This paper surveys deep neural network architectures that use semantic cues from image segmentation to improve stereo matching for depth estimation, comparing state-of-the-art methods in terms of accuracy and speed for real-time applications.
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.