Correlation based stereo matching has achieved outstanding performance, which pursues cost volume between two feature maps. Unfortunately, current methods with a fixed model do not work uniformly well across various datasets, greatly limiting their real-world applicability. To tackle this issue, this paper proposes a new perspective to dynamically calculate correlation for robust stereo matching. A novel Uncertainty Guided Adaptive Correlation (UGAC) module is introduced to robustly adapt the same model for different scenarios. Specifically, a variance-based uncertainty estimation is employed to adaptively adjust the sampling area during warping operation. Additionally, we improve the traditional non-parametric warping with learnable parameters, such that the position-specific weights can be learned. We show that by empowering the recurrent network with the UGAC module, stereo matching can be exploited more robustly and effectively. Extensive experiments demonstrate that our method achieves state-of-the-art performance over the ETH3D, KITTI, and Middlebury datasets when employing the same fixed model over these datasets without any retraining procedure. To target real-time applications, we further design a lightweight model based on UGAC, which also outperforms other methods over KITTI benchmarks with only 0.6 M parameters.

翻译：基于相关性的立体匹配通过构建两个特征图之间的代价体积取得了卓越性能。然而，现有固定模型的方法在不同数据集上无法实现一致优异的性能，极大限制了其实际应用。针对这一问题，本文提出从新视角动态计算相关性以实现鲁棒立体匹配。我们引入了一种新颖的不确定性引导自适应相关（UGAC）模块，使同一模型能够鲁棒地适应不同场景。具体而言，该方法采用基于方差的 uncertainty 估计来动态调整扭曲操作中的采样区域。此外，我们通过引入可学习参数改进了传统非参数化扭曲方法，使得位置特定权重可被学习。研究表明，将UGAC模块融入循环网络能够更鲁棒且高效地实现立体匹配。大量实验证明，在使用同一固定模型且无需重新训练的情况下，我们的方法在ETH3D、KITTI和Middlebury数据集上均达到了最先进性能。针对实时应用需求，我们进一步设计了基于UGAC的轻量级模型，该模型在KITTI基准上仅用0.6M参数即超越其他方法。