# CNN-based Cost Volume Analysis as Confidence Measure for Dense Matching

## TL;DR

This paper introduces a CNN architecture that leverages 3D cost volume data for improved confidence estimation in dense stereo matching, achieving state-of-the-art accuracy across multiple datasets.

## Contribution

It presents a novel deep learning method that directly uses volumetric 3D cost data for confidence estimation, enhancing accuracy over existing feature-based approaches.

## Key findings

- Achieves state-of-the-art confidence estimation accuracy
- Demonstrates generality across different stereo matching techniques
- Outperforms methods relying solely on disparity map features

## Abstract

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.