Monocular depth estimation is a very challenging task in computer vision, with the goal to predict per-pixel depth from a single RGB image. Supervised learning methods require large amounts of depth measurement data, which are time-consuming and expensive to obtain. Self-supervised methods are showing great promise, exploiting geometry to provide supervision signals through image warping. Moreover, several works leverage on other visual tasks (e.g. stereo matching and semantic segmentation) to further advance self-supervised monocular depth estimation. In this paper, we propose a novel framework utilizing monocular depth completion as an auxiliary task to assist monocular depth estimation. In particular, a knowledge transfer strategy is employed to enable monocular depth estimation to benefit from the effective feature representations learned by monocular depth completion task. The correlation between monocular depth completion and monocular depth estimation could be fully and effectively utilized in this framework. Only unlabeled stereo images are used in the proposed framework, which achieves a self-supervised learning paradigm. Experimental results on publicly available dataset prove that the proposed approach achieves superior performance to state-of-the-art self-supervised methods and comparable performance with supervised methods.

单目深度估计是计算机视觉中一项非常具有挑战性的任务，其目标是从单个 RGB 图像预测每像素深度。监督学习方法需要大量的深度测量数据，获取这些数据既耗时又昂贵。自监督方法显示出巨大的前景，利用几何形状通过图像变形提供监督信号。此外，一些工作利用其他视觉任务（例如立体匹配和语义分割）来进一步推进自我监督的单眼深度估计。在本文中，我们提出了一种利用单眼深度补全作为辅助任务来辅助单眼深度估计的新框架。特别是，采用知识转移策略使单眼深度估计能够从单眼深度完成任务学习的有效特征表示中受益。该框架可以充分有效地利用单眼深度补全和单眼深度估计之间的相关性。在所提出的框架中仅使用未标记的立体图像，从而实现了自监督学习范式。在公开可用数据集上的实验结果证明，所提出的方法比最先进的自监督方法具有优越的性能，并且与监督方法的性能相当。在所提出的框架中仅使用未标记的立体图像，从而实现了自监督学习范式。在公开可用数据集上的实验结果证明，所提出的方法比最先进的自监督方法具有优越的性能，并且与监督方法的性能相当。在所提出的框架中仅使用未标记的立体图像，从而实现了自监督学习范式。在公开可用数据集上的实验结果证明，所提出的方法比最先进的自监督方法具有优越的性能，并且与监督方法的性能相当。