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

Abstract. The ability to identify erroneous depth estimates is of fundamental interest. Information regarding the aleatoric uncertainty of depth estimates can be, for example, used to support the process of depth reconstruction itself. Consequently, various methods for the estimation of aleatoric uncertainty in the context of dense stereo matching have been presented in recent years, with deep learning-based approaches being particularly popular. Among these deep learning-based methods, probabilistic strategies are increasingly attracting interest, because the estimated uncertainty can be quantified in pixels or in metric units due to the consideration of real error distributions. However, existing probabilistic methods usually assume a unimodal distribution to describe the error distribution while simply neglecting cases in real-world scenarios that could violate this assumption. To overcome this limitation, we propose two novel mixed probability models consisting of Laplacian and Uniform distributions for the task of aleatoric uncertainty estimation. In this way, we explicitly address commonly challenging regions in the context of dense stereo matching and outlier measurements, respectively. To allow a fair comparison, we adapt a common neural network architecture to investigate the effects of the different uncertainty models. In an extensive evaluation using two datasets and two common dense stereo matching methods, the proposed methods demonstrate state-of-the-art accuracy.

Download Full-text

UNCERTAINTY ESTIMATION FOR END-TO-END LEARNED DENSE STEREO MATCHING VIA PROBABILISTIC DEEP LEARNING

ISPRS Annals of Photogrammetry Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-annals-v-2-2020-161-2020 ◽

2020 ◽

Vol V-2-2020 ◽

pp. 161-169

Author(s):

M. Mehltretter

Keyword(s):

Neural Network ◽

Deep Learning ◽

Stereo Matching ◽

Probabilistic Neural Network ◽

Uncertainty Estimation ◽

Training Data ◽

Stereo Image ◽

Confidence Estimation ◽

Extensive Evaluation ◽

Dense Stereo Matching

Abstract. Motivated by the need to identify erroneous disparity assignments, various approaches for uncertainty and confidence estimation of dense stereo matching have been presented in recent years. As in many other fields, especially deep learning based methods have shown convincing results. However, most of these methods only model the uncertainty contained in the data, while ignoring the uncertainty of the employed dense stereo matching procedure. Additionally modelling the latter, however, is particularly beneficial if the domain of the training data varies from that of the data to be processed. For this purpose, in the present work the idea of probabilistic deep learning is applied to the task of dense stereo matching for the first time. Based on the well-known and commonly employed GC-Net architecture, a novel probabilistic neural network is presented, for the task of joint depth and uncertainty estimation from epipolar rectified stereo image pairs. Instead of learning the network parameters directly, the proposed probabilistic neural network learns a probability distribution from which parameters are sampled for every prediction. The variations between multiple such predictions on the same image pair allow to approximate the model uncertainty. The quality of the estimated depth and uncertainty information is assessed in an extensive evaluation on three different datasets.

Download Full-text