Uncertainty estimation for stereo matching based on evidential deep learning

作者：

Highlights：

• A novel aleatoric and epistemic uncertainty estimation approach for stereo matching based on evidential deep learning.

• Two loss functions to utilize pixels without ground truth disparity to constrain uncertainty parameters.

• The proposed method improves stereo matching performance and assigns high uncertainty to incorrect estimation.

• The proposed method can also capture increased epistemic uncertainty when there is out-of-distribution data.

摘要

•A novel aleatoric and epistemic uncertainty estimation approach for stereo matching based on evidential deep learning.•Two loss functions to utilize pixels without ground truth disparity to constrain uncertainty parameters.•The proposed method improves stereo matching performance and assigns high uncertainty to incorrect estimation.•The proposed method can also capture increased epistemic uncertainty when there is out-of-distribution data.

论文关键词：Stereo matching,Uncertainty estimation,Evidential deep learning

论文评审过程：Received 19 May 2021, Revised 24 November 2021, Accepted 8 December 2021, Available online 11 December 2021, Version of Record 23 December 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108498