Multi-scale cross-form pyramid network for stereo matching

Zhidong Zhu, Mingyi He, Yuchao Dai, Zhibo Rao, Bo Li

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

23 Scopus citations

Abstract

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.

Original languageEnglish
Title of host publicationProceedings of the 14th IEEE Conference on Industrial Electronics and Applications, ICIEA 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1789-1794
Number of pages6
ISBN (Electronic)9781538694909
DOIs
StatePublished - Jun 2019
Event14th IEEE Conference on Industrial Electronics and Applications, ICIEA 2019 - Xi'an, China
Duration: 19 Jun 201921 Jun 2019

Publication series

NameProceedings of the 14th IEEE Conference on Industrial Electronics and Applications, ICIEA 2019

Conference

Conference14th IEEE Conference on Industrial Electronics and Applications, ICIEA 2019
Country/TerritoryChina
CityXi'an
Period19/06/1921/06/19

Keywords

  • Cross-form Spatial Pyramid Architecture
  • Multi-scale 3D Feature Matching and Fusion
  • Stereo Matching

Fingerprint

Dive into the research topics of 'Multi-scale cross-form pyramid network for stereo matching'. Together they form a unique fingerprint.

Cite this