Uncertainty Quantification in Stereo Matching

2024-12-24

AI Summary

Existing stereo matching methods lack explicit uncertainty modeling and fail to distinguish between aleatoric uncertainty (inherent data noise) and epistemic uncertainty (model ignorance). To address this, we propose the first decoupled Bayesian uncertainty quantification framework for stereo matching. Our method introduces a stereo-specific mechanism for jointly estimating aleatoric and epistemic uncertainties, unified under a Bayesian risk objective that enables interpretable and verifiable uncertainty calibration. Extensive evaluation on four major benchmarks—SceneFlow, KITTI, ETH3D, and Middlebury—demonstrates substantial improvements in uncertainty estimation quality. Moreover, leveraging low-risk sample selection guided by our uncertainty estimates yields consistent gains in disparity prediction accuracy. The framework is fully reproducible, and the source code is publicly released.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Uncertainty Representations
• Intelligent Robots: State Estimation

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

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 often provide limited interpretations of uncertainty and struggle to separate it effectively into data (aleatoric) and model (epistemic) components. This disentanglement 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 framework for stereo matching and its uncertainty quantification. We adopt Bayes risk as a measure of uncertainty and estimate data and model uncertainty separately. Experiments are conducted on four stereo benchmarks, and the results demonstrate that our method can estimate uncertainty accurately and efficiently. Furthermore, we apply our uncertainty method to improve prediction accuracy by selecting data points with small uncertainties, which reflects the accuracy of our estimated uncertainty. The codes are publicly available at https://github.com/RussRobin/Uncertainty.

Problem

• stereo imaging
• uncertainty quantification
• reliability enhancement

Innovation

• Bayesian risk
• stereo image matching
• uncertainty quantification