Search papers, labs, and topics across Lattice.
This paper introduces URS-Stereo, a novel framework for real-time stereo matching that enhances disparity accuracy by incorporating uncertainty-guided search adaptation. The method utilizes an Uncertainty-Guided Residual Search Module (UGRSM) to predict the reliability of propagated disparities and dynamically adjust the local search regions, effectively mitigating matching failures caused by inaccurate disparity estimates. Experimental results across multiple datasets, including SceneFlow and KITTI, show that URS-Stereo significantly improves disparity estimation while maintaining real-time processing speeds, highlighting its robustness and efficiency in practical applications.
Uncertainty-guided search adaptation allows URS-Stereo to recover from disparity estimation errors that would typically lead to unrecoverable matching failures.
Real-time stereo matching is crucial for robotics, autonomous systems, and embedded vision applications, where both computational efficiency and disparity accuracy are required. Recent coarse-to-fine stereo matching methods improve efficiency by progressively refining disparity estimates using local cost volumes at higher resolutions. However, these methods rely heavily on the accuracy of propagated disparity estimates from previous stages. When the propagated disparity is inaccurate, the ground-truth correspondence may fall outside the predefined local search range, leading to unrecoverable matching failures during subsequent refinement. In this paper, we propose URS-Stereo, a real-time coarse-to-fine stereo matching framework that addresses this limitation through uncertainty-guided search adaptation. Specifically, we introduce an Uncertainty-Guided Residual Search Module (UGRSM), which predicts the reliability of propagated disparities together with residual search offsets to adaptively relocate the centers of local cost volumes before disparity refinement. By dynamically adjusting the search region according to the confidence of the propagated disparity, the proposed method significantly improves the robustness of local correspondence estimation while preserving the computational efficiency of coarse-to-fine stereo matching. Extensive experiments on SceneFlow, KITTI 2012, KITTI 2015, Middlebury, and ETH3D demonstrate that URS-Stereo consistently improves disparity estimation while maintaining real-time inference speed, validating the effectiveness of the proposed uncertainty-guided search strategy
