Based on well-designed network architectures and objective functions, self-supervised monocular depth estimation has made great progress. However, lacking a specific mechanism to make the network learn more about the regions containing moving objects or occlusion scenarios, existing depth estimation methods likely produce poor results for them. Therefore, we propose an uncertainty quantification method to improve the performance of existing depth estimation networks without changing their architectures. Our uncertainty quantification method consists of uncertainty measurement, the learning guidance by uncertainty, and the ultimate adaptive determination. Firstly, with Snapshot and Siam learning strategies, we measure the uncertainty degree by calculating the variance of pre-converged epochs or twins during training. Secondly, we use the uncertainty to guide the network to strengthen learning about those regions with more uncertainty. Finally, we use the uncertainty to adaptively produce the final depth estimation results with a balance of accuracy and robustness. To demonstrate the effectiveness of our uncertainty quantification method, we apply it to two state-of-the-art models, Monodepth2 and Hints. Experimental results show that our method has improved the depth estimation performance in seven evaluation metrics compared with two baseline models and exceeded the existing uncertainty method.

基于精心设计的网络架构和目标函数，自监督单目深度估计取得了长足的进步。然而，由于缺乏特定的机制来使网络更多地了解包含移动物体或遮挡场景的区域，现有的深度估计方法可能会产生较差的结果。因此，我们提出了一种不确定性量化方法来提高现有深度估计网络的性能而不改变其架构。我们的不确定性量化方法包括不确定性测量、不确定性的学习指导和最终的自适应确定。首先，使用 Snapshot 和 Siam 学习策略，我们通过计算训练过程中预收敛 epoch 或孪生的方差来测量不确定性程度。第二，我们利用不确定性来引导网络加强对那些不确定性较多的区域的学习。最后，我们利用不确定性自适应地产生最终的深度估计结果，并在准确性和鲁棒性之间取得平衡。为了证明我们的不确定性量化方法的有效性，我们将其应用于两个最先进的模型：Monodepth2 和 Hints。实验结果表明，与两个基线模型相比，我们的方法在七个评估指标上提高了深度估计性能，并超越了现有的不确定性方法。为了证明我们的不确定性量化方法的有效性，我们将其应用于两个最先进的模型：Monodepth2 和 Hints。实验结果表明，与两个基线模型相比，我们的方法在七个评估指标上提高了深度估计性能，并超越了现有的不确定性方法。为了证明我们的不确定性量化方法的有效性，我们将其应用于两个最先进的模型：Monodepth2 和 Hints。实验结果表明，与两个基线模型相比，我们的方法在七个评估指标上提高了深度估计性能，并超越了现有的不确定性方法。