CNN-based Cost Volume Analysis as Confidence Measure for Dense Matching
This work addresses the need for reliable confidence measures in applications like autonomous driving, offering an incremental improvement by integrating cost volume features into deep learning methods.
The paper tackles the problem of confidence estimation in dense stereo matching by proposing a CNN architecture that learns features directly from 3D cost volumes, achieving state-of-the-art accuracy on three datasets with three common matching techniques.
Due to its capability to identify erroneous disparity assignments in dense stereo matching, confidence estimation is beneficial for a wide range of applications, e.g. autonomous driving, which needs a high degree of confidence as mandatory prerequisite. Especially, the introduction of deep learning based methods resulted in an increasing popularity of this field in recent years, caused by a significantly improved accuracy. Despite this remarkable development, most of these methods rely on features learned from disparity maps only, not taking into account the corresponding 3-dimensional cost volumes. However, it was already demonstrated that with conventional methods based on hand-crafted features this additional information can be used to further increase the accuracy. In order to combine the advantages of deep learning and cost volume based features, in this paper, we propose a novel Convolutional Neural Network (CNN) architecture to directly learn features for confidence estimation from volumetric 3D data. An extensive evaluation on three datasets using three common dense stereo matching techniques demonstrates the generality and state-of-the-art accuracy of the proposed method.