Probabilistic modeling of disparity uncertainty for robust and efficient stereo matching
Cai, Wenxiao Hu, Dongting Yin, Ruoyan Deng, Jiankang Fu, Huan Yang, Wankou Gong, Mingming
Cai, Wenxiao
Hu, Dongting
Yin, Ruoyan
Deng, Jiankang
Fu, Huan
Yang, Wankou
Gong, Mingming
Supervisor
Department
Machine Learning
Embargo End Date
Type
Journal article
Date
License
Language
EEnglish
Collections
Research Projects
Organizational Units
Journal Issue
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.
Citation
W. Cai, D. Hu, R. Yin, J. Deng, H. Fu, W. Yang , et al., "Probabilistic modeling of disparity uncertainty for robust and efficient stereo matching," Pattern Recognition, vol. 175, pp. 113102-113102, 2026, https://doi.org/10.1016/j.patcog.2026.113102.
Source
Pattern Recognition
Conference
Keywords
46 Information and Computing Sciences, 4603 Computer Vision and Multimedia Computation
Subjects
Source
Publisher
Elsevier