期刊
SENSORS
卷 22, 期 12, 页码 -出版社
MDPI
DOI: 10.3390/s22124548
关键词
stereo matching; coarse-to-fine; depth map super-resolution; disparity regression; deep learning
资金
- Hubei Provincial Department of Education [21D031]
The study introduces a novel stereo matching network, ASR-Net, which combines multi-level residual optimization and depth map super-resolution to improve accuracy and speed. Experimental results demonstrate outstanding performance on different datasets, with the three-pixel error reducing to 2.86% for the kitti2015 dataset and surpassing traditional methods in terms of speed.
In order to avoid the direct depth reconstruction of the original image pair and improve the accuracy of the results, we proposed a coarse-to-fine stereo matching network combining multi-level residual optimization and depth map super-resolution (ASR-Net). First, we used the u-net feature extractor to obtain the multi-scale feature pair. Second, we reconstructed global disparity in the lowest resolution. Then, we regressed the residual disparity using the higher-resolution feature pair. Finally, the lowest-resolution depth map was refined by using the disparity residual. In addition, we introduced deformable convolution and group-wise cost volume into the network to achieve adaptive cost aggregation. Further, the network uses ABPN instead of the traditional interpolation method. The network was evaluated on three datasets: scene flow, kitti2015, and kitti2012 and the experimental results showed that the speed and accuracy of our method were excellent. On the kitti2015 dataset, the three-pixel error converged to 2.86%, and the speed was about six times and two times that of GC-net and GWC-net.
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。
推荐
暂无数据