Next Article in Journal
Investigation on Wireless Link for Medical Telemetry Including Impedance Matching of Implanted Antennas
Next Article in Special Issue
Optimizing 3D Convolution Kernels on Stereo Matching for Resource Efficient Computations
Previous Article in Journal
Underwater Acoustic Target Recognition Based on Depthwise Separable Convolution Neural Networks
Article

A Joint 2D-3D Complementary Network for Stereo Matching

College of Computer, National University of Defense Technology, Changsha 410073, China
*
Author to whom correspondence should be addressed.
These authors contributed equally to this work.
Academic Editors: Adrian Burlacu and Enric Cervera
Sensors 2021, 21(4), 1430; https://doi.org/10.3390/s21041430
Received: 26 January 2021 / Revised: 12 February 2021 / Accepted: 16 February 2021 / Published: 18 February 2021
Stereo matching is an important research field of computer vision. Due to the dimension of cost aggregation, current neural network-based stereo methods are difficult to trade-off speed and accuracy. To this end, we integrate fast 2D stereo methods with accurate 3D networks to improve performance and reduce running time. We leverage a 2D encoder-decoder network to generate a rough disparity map and construct a disparity range to guide the 3D aggregation network, which can significantly improve the accuracy and reduce the computational cost. We use a stacked hourglass structure to refine the disparity from coarse to fine. We evaluated our method on three public datasets. According to the KITTI official website results, Our network can generate an accurate result in 80 ms on a modern GPU. Compared to other 2D stereo networks (AANet, DeepPruner, FADNet, etc.), our network has a big improvement in accuracy. Meanwhile, it is significantly faster than other 3D stereo networks (5× than PSMNet, 7.5× than CSN and 22.5× than GANet, etc.), demonstrating the effectiveness of our method. View Full-Text
Keywords: stereo matching; depth estimation; computer vision stereo matching; depth estimation; computer vision
Show Figures

Figure 1

MDPI and ACS Style

Jia, X.; Chen, W.; Liang, Z.; Luo, X.; Wu, M.; Li, C.; He, Y.; Tan, Y.; Huang, L. A Joint 2D-3D Complementary Network for Stereo Matching. Sensors 2021, 21, 1430. https://doi.org/10.3390/s21041430

AMA Style

Jia X, Chen W, Liang Z, Luo X, Wu M, Li C, He Y, Tan Y, Huang L. A Joint 2D-3D Complementary Network for Stereo Matching. Sensors. 2021; 21(4):1430. https://doi.org/10.3390/s21041430

Chicago/Turabian Style

Jia, Xiaogang, Wei Chen, Zhengfa Liang, Xin Luo, Mingfei Wu, Chen Li, Yulin He, Yusong Tan, and Libo Huang. 2021. "A Joint 2D-3D Complementary Network for Stereo Matching" Sensors 21, no. 4: 1430. https://doi.org/10.3390/s21041430

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop