Group-Wise Correlation Stereo Network
Citations Over TimeTop 1% of 2019 papers
Abstract
Stereo matching estimates the disparity between a rectified image pair, which is of great importance to depth sensing, autonomous driving, and other related tasks. Previous works built cost volumes with cross-correlation or concatenation of left and right features across all disparity levels, and then a 2D or 3D convolutional neural network is utilized to regress the disparity maps. In this paper, we propose to construct the cost volume by group-wise correlation. The left features and the right features are divided into groups along the channel dimension, and correlation maps are computed among each group to obtain multiple matching cost proposals, which are then packed into a cost volume. Group-wise correlation provides efficient representations for measuring feature similarities and will not lose too much information like full correlation. It also preserves better performance when reducing parameters compared with previous methods. The 3D stacked hourglass network proposed in previous works is improved to boost the performance and decrease the inference computational cost. Experiment results show that our method outperforms previous methods on Scene Flow, KITTI 2012, and KITTI 2015 datasets.
Related Papers
- Korean text-to-speech and concatenation cost function(2006)
- Applications of Virtual Concatenation in Digital Wrapper Technology(2003)
- → A Chinese Text Classification Method With Low Hardware Requirement Based on Improved Model Concatenation(2020)
- → Concatenations of Terms of an Arithmetic Progression(2022)
- → Concatenation-Informer: Pre-Distilling and Concatenation Improve Efficiency and Accuracy(2023)