Centre de documentation
scientifique

Uncertainty estimation for stereo matching based on evidential deep learning / Chen Wang in Pattern recognition, vol 124 (April 2022)  

Public [article]  inPattern recognition > vol 124 (April 2022) . - n° 108498 Titre : Uncertainty estimation for stereo matching based on evidential deep learning Type de document : Article/Communication Auteurs : Chen Wang, Auteur ; Xiang Wang, Auteur ; Jiawei Zhang, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 108498 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] appariement d'images [Termes IGN] apprentissage profond [Termes IGN] distribution de Gauss [Termes IGN] fonction de perte [Termes IGN] lissage de données [Termes IGN] modèle d'incertitude [Termes IGN] reconstruction d'image Résumé : (auteur) 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. Numéro de notice : A2022-198 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article DOI : 10.1016/j.patcog.2021.108498 Date de publication en ligne : 23/12/2021 En ligne : https://doi.org/10.1016/j.patcog.2021.108498 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99992 [article]