Uncertainty estimation for stereo matching based on evidential deep learning. (April 2022)

• Record Type: Journal Article
• Authors: Wang, Chen; Wang, Xiang; Zhang, Jiawei; Zhang, Liang; Bai, Xiao; Ning, Xin; Zhou, Jun; Hancock, Edwin
• Is Part Of: Pattern recognition. Volume 124(2022)
• Publication Date: 2022-04
• Subjects: Stereo matching -- Uncertainty estimation -- Evidential deep learning; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2021.108498
• Languages: English
• ISSNs: 0031-3203

Abstract

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. Abstract: Although deep learning-based stereo matching approaches have achieved excellent performance in recent years, it is still a non-trivial task to estimate the uncertainty of the produced disparity map. In this paper, we propose a novel approach to estimate both aleatoric and epistemic uncertainties for stereo matching in an end-to-end way. We introduce an evidential distribution, named Normal Inverse-Gamma (NIG) distribution, whose parameters can be used to calculate the uncertainty. Instead of directly regressed from aggregated features, the uncertainty parameters are predicted for each potential disparity and then averaged via the guidance of matching probability distribution. Furthermore, considering the sparsity of ground truth in real scene datasets, we design two additional losses. The first one tries to enlarge uncertainty on incorrect predictions, so uncertainty becomes more sensitive to erroneous regions. The second one enforces the smoothness of the uncertainty in the regions with smooth disparity. Most stereo matching models, such as PSM-Net, GA-Net, and AA-Net, can be easily integrated with our approach. Experiments on multiple benchmark datasets show that our method improves stereo matching results. We prove that both aleatoric and epistemic uncertainties are well-calibrated with incorrect predictions. Particularly, our method can capture increased epistemic uncertainty on out-of-distribution data, making it effective to prevent a system from potential fatal consequences. Code is available at https://github.com/Dawnstar8411/StereoMatching-Uncertainty .