TY - GEN
T1 - Multi-scale cross-form pyramid network for stereo matching
AU - Zhu, Zhidong
AU - He, Mingyi
AU - Dai, Yuchao
AU - Rao, Zhibo
AU - Li, Bo
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/6
Y1 - 2019/6
N2 - Stereo matching plays an indispensable part in autonomous driving, robotics and 3D scene reconstruction. We propose a novel deep learning architecture, which called CFP-Net, a Cross-Form Pyramid stereo matching network for regressing disparity from a rectified pair of stereo images. The network consists of three modules: Multi-Scale 2D local feature extraction module, Cross-form spatial pyramid module and Multi-Scale 3D Feature Matching and Fusion module. The Multi-Scale 2D local feature extraction module can extract enough multi-scale features. The Cross-form spatial pyramid module aggregates the context information in different scales and locations to form a cost volume. Moreover, it is proved to be more effective than SPP and ASPP in ill-posed regions. The Multi-Scale 3D feature matching and fusion module is proved to regularize the cost volume using two parallel 3D deconvolution structure with two different receptive fields. Our proposed method has been evaluated on the Scene Flow and KITTI datasets. It achieves state-of-the-art performance on the KITTI 2012 and 2015 benchmarks.
AB - Stereo matching plays an indispensable part in autonomous driving, robotics and 3D scene reconstruction. We propose a novel deep learning architecture, which called CFP-Net, a Cross-Form Pyramid stereo matching network for regressing disparity from a rectified pair of stereo images. The network consists of three modules: Multi-Scale 2D local feature extraction module, Cross-form spatial pyramid module and Multi-Scale 3D Feature Matching and Fusion module. The Multi-Scale 2D local feature extraction module can extract enough multi-scale features. The Cross-form spatial pyramid module aggregates the context information in different scales and locations to form a cost volume. Moreover, it is proved to be more effective than SPP and ASPP in ill-posed regions. The Multi-Scale 3D feature matching and fusion module is proved to regularize the cost volume using two parallel 3D deconvolution structure with two different receptive fields. Our proposed method has been evaluated on the Scene Flow and KITTI datasets. It achieves state-of-the-art performance on the KITTI 2012 and 2015 benchmarks.
KW - Cross-form Spatial Pyramid Architecture
KW - Multi-scale 3D Feature Matching and Fusion
KW - Stereo Matching
UR - http://www.scopus.com/inward/record.url?scp=85073053130&partnerID=8YFLogxK
U2 - 10.1109/ICIEA.2019.8834193
DO - 10.1109/ICIEA.2019.8834193
M3 - 会议稿件
AN - SCOPUS:85073053130
T3 - Proceedings of the 14th IEEE Conference on Industrial Electronics and Applications, ICIEA 2019
SP - 1789
EP - 1794
BT - Proceedings of the 14th IEEE Conference on Industrial Electronics and Applications, ICIEA 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 14th IEEE Conference on Industrial Electronics and Applications, ICIEA 2019
Y2 - 19 June 2019 through 21 June 2019
ER -