Rectified Iterative Disparity for Stereo Matching

TL;DR

This work tackles accurate stereo disparity estimation by introducing a cost-volume-based uncertainty estimation (UEC) that jointly predicts disparity and uncertainty with low overhead. Building on UEC, it proposes Uncertainty-based Disparity Rectification (UDR) and Uncertainty-based Disparity update Conditioning (UDC) to steer iterative disparity refinement, complemented by a Disparity Rectification loss (DR loss) that emphasizes small-error updates. The resulting DR-Stereo architecture achieves competitive performance on Scene Flow, KITTI, Middlebury 2014, and ETH3D, with strong zero-shot generalization, demonstrating efficient, uncertainty-aware stereo without extra networks. These contributions advance the practicality of uncertainty-guided, iterative stereo methods by reducing computational burden while improving robustness across domains.

Abstract

Both uncertainty-assisted and iteration-based methods have achieved great success in stereo matching. However, existing uncertainty estimation methods take a single image and the corresponding disparity as input, which imposes higher demands on the estimation network. In this paper, we propose Cost volume-based disparity Uncertainty Estimation (UEC). Based on the rich similarity information in the cost volume coming from the image pairs, the proposed UEC can achieve competitive performance with low computational cost. Secondly, we propose two methods of uncertainty-assisted disparity estimation, Uncertainty-based Disparity Rectification (UDR) and Uncertainty-based Disparity update Conditioning (UDC). These two methods optimise the disparity update process of the iterative-based approach without adding extra parameters. In addition, we propose Disparity Rectification loss that significantly improves the accuracy of small amount of disparity updates. We present a high-performance stereo architecture, DR Stereo, which is a combination of the proposed methods. Experimental results from SceneFlow, KITTI, Middlebury 2014, and ETH3D show that DR-Stereo achieves very competitive disparity estimation performance.

Figures (5)

• Figure 1: The cost volume-based disparity uncertainty estimation. This figure compares the architecture between the previous work and ours. The previous work only utilises information from the left image. Our work makes full use of the information in the image pairs and avoids redundant feature extraction steps.
• Figure 2: Overview of our proposed DR-Stereo. We estimate the disparity uncertainty by cost volume. The init disparity is coarsely optimised once in the UDR and then finely optimised several times through the iterative unit. In the iterative unit, the proposed UDC moderates the disparity update to keep the update range stable.
• Figure 3: The qualitative results of UEC on Middlebury 2014. The error distribution of disparity is plotted with the largest error in the red region and the smallest error in the blue region. We pre-train our model on Scene Flow and test it directly on Middlebury 2014. On the new domain, the sensitivity of UEC to disparity error is superior to that of task-separated architectures.
• Figure 4: The effect of UDC in the disparity update process. We mosaic over the initial disparity to simulate the disparity update process in extreme cases. Test image from Middlebury 2014. The baseline is IGEV-Stereo.
• Figure 5: Splitting process of UDC on different datasets.