Multiscale Feature Extractors for Stereo Matching Cost Computation

Kyung Rae Kim, Yeong Jun Koh, Chang-Su Kim

Research output: Contribution to journalArticlepeer-review

12 Citations (Scopus)


We propose four efficient feature extractors based on convolutional neural networks for stereo matching cost computation. Two of them generate multiscale features with diverse receptive field sizes. These multiscale features are used to compute the corresponding multiscale matching costs. We then determine an optimal cost by combining the multiscale costs using edge information. On the other hand, the other two feature extractors produce uni-scale features by combining multiscale features directly through fully connected layers. Finally, after obtaining matching costs using one of the four extractors, we determine optimal disparities based on the cross-based cost aggregation and the semiglobal matching. Extensive experiments on the Middlebury stereo data sets demonstrate the effectiveness and efficiency of the proposed algorithm. Specifically, the proposed algorithm provides competitive matching performance with the state of the arts, while demanding lower computational complexity.

Original languageEnglish
Pages (from-to)27971-27983
Number of pages13
JournalIEEE Access
Publication statusPublished - 2018 May 17

Bibliographical note

Funding Information:
This work was supported in part by the Cross-Ministry Giga KOREA Project Grant funded by the Korean Government (MSIT) (development of 4D reconstruction and dynamic deformable action model based hyper-realistic service technology) under Grant GK18P0200 and in part by the National Research Foundation of Korea Grant funded by the Korean Government (MSIP) under Grant NRF-2015R1A2A1A10055037 and Grant NRF-2018R1A2B3003896.

Publisher Copyright:
© 2013 IEEE.


  • Stereo matching
  • convolutional neural networks
  • matching cost computation
  • multiscale feature extraction

ASJC Scopus subject areas

  • General Computer Science
  • General Materials Science
  • General Engineering


Dive into the research topics of 'Multiscale Feature Extractors for Stereo Matching Cost Computation'. Together they form a unique fingerprint.

Cite this