Noise-Sampling Cross Entropy Loss: Improving Disparity Regression Via Cost Volume Aware Regularizer

TL;DR

This paper introduces a novel noise-sampling cross entropy loss that regularizes the cost volume in disparity regression neural networks, leading to improved stereo matching accuracy by enforcing unimodality and coherence.

Contribution

It proposes a new loss function that explicitly constrains the cost volume in deep disparity estimation, addressing a gap in traditional end-to-end methods.

Findings

Enhanced cost volume quality with the proposed loss.

Improved stereo matching performance over existing algorithms.

Better learning of informative cost volumes in neural networks.

Abstract

Recent end-to-end deep neural networks for disparity regression have achieved the state-of-the-art performance. However, many well-acknowledged specific properties of disparity estimation are omitted in these deep learning algorithms. Especially, matching cost volume, one of the most important procedure, is treated as a normal intermediate feature for the following softargmin regression, lacking explicit constraints compared with those traditional algorithms. In this paper, inspired by previous canonical definition of cost volume, we propose the noise-sampling cross entropy loss function to regularize the cost volume produced by deep neural networks to be unimodal and coherent. Extensive experiments validate that the proposed noise-sampling cross entropy loss can not only help neural networks learn more informative cost volume, but also lead to better stereo matching performance compared with several representative algorithms.