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.

通过引入新的不确定性引导自适应相关性 (UGAC) 模块，本文提出一种动态计算相关性以实现鲁棒立体匹配的新视角。通过适应性调整采样区域和学习参数，UGAC 模块使得立体匹配能够更加鲁棒和高效地进行。实验证明，在 ETH3D、KITTI 和 Middlebury 数据集上，即使在没有任何再训练过程的情况下，采用相同的固定模型，我们的方法也能够实现最先进的性能。此外，为了针对实时应用，我们还设计了一个基于 UGAC 的轻量级模型，在只有 0.6 M 参数的情况下，在 KITTI 基准上也胜过其他方法。