Aleatoric uncertainty estimation for dense stereo matching via CNN-based cost volume analysis

Motivated by the need to identify erroneous disparity estimates, various methods for the estimation of aleatoric uncertainty in the context of dense stereo matching have been presented in recent years. Especially, the introduction of deep learning based methods and the accompanying significant improvement in accuracy have greatly increased the popularity of this field. Despite this remarkable development, most of these methods rely on features learned from disparity maps only, neglecting the corresponding 3-dimensional cost volumes. However, conventional hand-crafted methods have already demonstrated that the additional information contained in such cost volumes are beneficial for the task of uncertainty estimation. In this paper, we combine the advantages of deep learning and cost volume based features and present a new Convolutional Neural Network (CNN) architecture to directly learn features for the task of aleatoric uncertainty estimation from volumetric 3D data. Furthermore, we discuss and apply three different uncertainty models to train our CNN without the need to provide ground truth for uncertainty. In an extensive evaluation on three datasets using three common dense stereo matching methods, we investigate the effects of these uncertainty models and demonstrate the generality and state-of-the-art accuracy of the proposed method.

Automated summary

This study combines the advantages of deep learning and cost volume-based features to propose a new Convolutional Neural Network (CNN) architecture for learning features from volumetric 3D data for uncertainty estimation. Three different uncertainty models are discussed and applied to train the CNN, showing the generality and state-of-the-art accuracy of the proposed method in extensive evaluations on three datasets using three common dense stereo matching methods.