Multiple Frequency Inputs and Context-Guided Attention Network for Stereo Disparity Estimation
-
Published:2022-06-07
Issue:12
Volume:11
Page:1803
-
ISSN:2079-9292
-
Container-title:Electronics
-
language:en
-
Short-container-title:Electronics
Author:
Hua Yan,Yang Lin,Yang Yingyun
Abstract
Deep learning-based methods have made remarkable progress for stereo matching in terms of accuracy. However, two issues still hinder producing a perfect disparity map: (1) blurred boundaries and the discontinuous disparity of a continuous region on disparity estimation maps, and (2) a lack of effective means to restore resolution precisely. In this paper, we propose to utilize multiple frequency inputs and an attention mechanism to construct the deep stereo matching model. Specifically, high-frequency and low-frequency information of the input image together with the RGB image are fed into a feature extraction network with 2D convolutions. It is conducive to produce a distinct boundary and continuous disparity of the smooth region on disparity maps. To regularize the 4D cost volume for disparity regression, we propose a 3D context-guided attention module for stacked hourglass networks, where high-level cost volumes as context guide low-level features to obtain high-resolution yet precise feature maps. The proposed approach achieves competitive performance on SceneFlow and KITTI 2015 datasets.
Funder
National Key Research and Development Program of China
National Natural Science Foundation of China
Subject
Electrical and Electronic Engineering,Computer Networks and Communications,Hardware and Architecture,Signal Processing,Control and Systems Engineering
Reference38 articles.
1. Depth map prediction from a single image using a multi-scale deep network;Eigen;Proceedings of the International Conference on Neural Information Processing Systems,2014
2. Pyramid Stereo Matching Network;Chang;Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,2018
3. NLCA-Net: a non-local context attention network for stereo matching
4. End-to-end learning of geometry and context for deep stereo regression;Kendall;Proceedings of the IEEE International Conference on Computer Vision,2017
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献