A fast stereo matching network with multi-cross attention

doi:10.3390/s21186016

CIOMP OpenIR

	A fast stereo matching network with multi-cross attention
	M. Wei; M. Zhu; Y. Wu; J. Sun; J. Wang and C. Liu
	2021
发表期刊	Sensors
ISSN	14248220
卷号	21 期号:18
摘要	Stereo matching networks based on deep learning are widely developed and can obtain excellent disparity estimation. We present a new end-to-end fast deep learning stereo matching network in this work that aims to determine the corresponding disparity from two stereo image pairs. We extract the characteristics of the low-resolution feature images using the stacked hourglass structure feature extractor and build a multi-level detailed cost volume. We also use the edge of the left image to guide disparity optimization and sub-sample with the low-resolution data, ensuring excellent accuracy and speed at the same time. Furthermore, we design a multi-cross attention model for binocular stereo matching to improve the matching accuracy and achieve end-to-end disparity regression effectively. We evaluate our network on Scene Flow, KITTI2012, and KITTI2015 datasets, and the experimental results show that the speed and accuracy of our method are excellent. 2021 by the authors. Licensee MDPI, Basel, Switzerland.
DOI	10.3390/s21186016
URL	查看原文
收录类别	SCI ; EI
引用统计
文献类型	期刊论文
条目标识符	http://ir.ciomp.ac.cn/handle/181722/65245
专题	中国科学院长春光学精密机械与物理研究所
推荐引用方式 GB/T 7714	M. Wei,M. Zhu,Y. Wu,et al. A fast stereo matching network with multi-cross attention[J]. Sensors,2021,21(18).
APA	M. Wei,M. Zhu,Y. Wu,J. Sun,&J. Wang and C. Liu.(2021).A fast stereo matching network with multi-cross attention.Sensors,21(18).
MLA	M. Wei,et al."A fast stereo matching network with multi-cross attention".Sensors 21.18(2021).

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
A fast stereo matchi（8611KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载