Probabilistic Modeling of Disparity Uncertainty for Robust and Efficient Stereo Matching

TL;DR

This paper introduces a probabilistic stereo matching framework that effectively estimates and separates data and model uncertainty, improving interpretability and reliability in disparity estimation without compromising accuracy.

Contribution

It proposes a novel uncertainty-aware stereo matching method using Bayes risk, enabling efficient and accurate uncertainty estimation and analysis.

Findings

Accurately estimates data and model uncertainty in stereo matching.

Efficiently analyzes uncertainty without additional training.

Maintains disparity prediction accuracy while estimating uncertainty.

Abstract

Stereo matching plays a crucial role in various applications, where understanding uncertainty can enhance both safety and reliability. Despite this, the estimation and analysis of uncertainty in stereo matching have been largely overlooked. Previous works struggle to separate it into data (aleatoric) and model (epistemic) components and often provide limited interpretations of uncertainty. This interpretability is essential, as it allows for a clearer understanding of the underlying sources of error, enhancing both prediction confidence and decision-making processes. In this paper, we propose a new uncertainty-aware stereo matching framework. We adopt Bayes risk as the measurement of uncertainty and use it to separately estimate data and model uncertainty. We systematically analyze data uncertainty based on the probabilistic distribution of disparity and efficiently estimate model uncertainty without repeated model training. Experiments are conducted on four stereo benchmarks, and the results demonstrate that our method can estimate uncertainty accurately and efficiently, without sacrificing the disparity prediction accuracy.