EDNet: Efficient Disparity Estimation with Cost Volume Combination and Attention-based Spatial Residual

Songyan Zhang, Zhicheng Wang*, Qiang Wang, Jinshuo Zhang, Gang Wei, Xiaowen Chu

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference contributionpeer-review

Abstract

Existing state-of-the-art disparity estimation works mostly leverage the 4D concatenation volume and construct a very deep 3D convolution neural network (CNN) for disparity regression, which is inefficient due to the high memory consumption and slow inference speed. In this paper, we propose a network named EDNet for efficient disparity estimation. Firstly, we construct a combined volume which incorporates contextual information from the squeezed concatenation volume and feature similarity measurement from the correlation volume. The combined volume can be next aggregated by 2D convolutions which are faster and require less memory than 3D convolutions. Secondly, we propose an attention-based spatial residual module to generate attention-aware residual features. The attention mechanism is applied to provide intuitive spatial evidence about inaccurate regions with the help of error maps at multiple scales and thus improve the residual learning efficiency. Extensive experiments on the Scene Flow and KITTI datasets show that EDNet outperforms the previous 3D CNN based works and achieves state-of-the-art performance with significantly faster speed and less memory consumption.

Original languageEnglish
Title of host publicationProceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021
PublisherIEEE
Pages5429-5438
Number of pages10
ISBN (Electronic)9781665445092
ISBN (Print)9781665445108
DOIs
Publication statusPublished - Jun 2021
Event34th IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021 - Virtual, Online, United States
Duration: 19 Jun 202125 Jun 2021

Publication series

NameProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
ISSN (Print)1063-6919
ISSN (Electronic)2575-7075

Conference

Conference34th IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021
Country/TerritoryUnited States
CityVirtual, Online
Period19/06/2125/06/21

Scopus Subject Areas

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'EDNet: Efficient Disparity Estimation with Cost Volume Combination and Attention-based Spatial Residual'. Together they form a unique fingerprint.

Cite this