4.4 Article

A light-weight stereo matching network based on multi-scale features fusion and robust disparity refinement

期刊

IET IMAGE PROCESSING
卷 17, 期 6, 页码 1797-1811

出版社

WILEY
DOI: 10.1049/ipr2.12756

关键词

computer vision; image processing; stereo image processing

向作者/读者索取更多资源

In this paper, a lightweight end-to-end network (LWNet) for fast stereo matching is proposed, which achieves competitive accuracy and speed compared to state-of-the-art methods. The network consists of an efficient backbone, 3D U-Net aggregation architecture, and color guidance for disparity computation and refinement.
In recent years, convolutional-neural-network based stereo matching methods have achieved significant gains compared to conventional methods in terms of both speed and accuracy. Current state-of-the-art disparity estimation algorithms require many parameters and large amounts of computational resources and are not suited for applications on edge devices. In this paper, an end-to-end light-weight network (LWNet) for fast stereo matching is proposed, which consists of an efficient backbone with multi-scale feature fusion for feature extraction, a 3D U-Net aggregation architecture for disparity computation, and color guidance in a 2D convolutional neural network (CNN) for disparity refinement. MobileNetV2 is adopted as an efficient backbone in feature extraction. The channel attention module is applied to improve the representational capacity of features and multi-resolution information is adaptively incorporated into the cost volume via cross-scale connections. Further, a left-right consistency check and color guidance refinement are introduced and a robust disparity refinement network is designed with skip connections and dilated convolutions to capture global context information and improve disparity estimation accuracy with little computational cost and memory space. Extensive experiments on Scene Flow, KITTI 2015, and KITTI 2012 demonstrate that the proposed LWNet achieves competitive accuracy and speed when compared with state-of-the-art stereo matching methods.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.4
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据