Monocular depth estimation has been carried out with convolutional neural networks (CNNs). However, vast quantities of ground truth depth data are required as a supervising signal. Recently, self-supervised learning is explored for monocular depth estimation, which uses the minor loss of image reconstruction, rather than depth information, as the supervising signal in the training phase. However, the blurring problem often occurs on the surface of a near object when using the image reconstruction as a major loss function. Here, we propose a novel Progressive Strategy Network (PSNet) to overcome this problem, which optimizes the depth map from coarse to fine with several progressive modules. A progressive module estimates a coarse depth map with a color image by CNNs and outputs it into the next module for progressively accurate refinement. It can simplify the difficulty of estimating the depth map with a large size and reduce the blurring problem. Experiments demonstrate that the proposed approach consistently improves the quality of depth map on the surface of large objects and keeps edges clear. Our proposed method performs high-quality depth estimation on the KITTI dataset and achieves a strong generalization on the Make3D dataset. Besides, it can be flexibly used on the real scenes captured by mobile phones without extra training.

中文翻译：

---

基于渐进策略的单眼深度估计的自我监督学习

已经使用卷积神经网络（CNN）进行了单眼深度估计。但是，需要大量地面真实深度数据作为监控信号。近来，探索了用于单眼深度估计的自我监督学习，其使用图像重建的少量损失而不是深度信息作为训练阶段的监督信号。然而，当使用图像重建作为主要损失函数时，模糊问题经常出现在附近物体的表面上。在这里，我们提出了一个新颖的渐进策略网络（PSNet）来解决此问题，该网络使用多个渐进模块将深度图从粗略优化为精细。渐进式模块通过CNN估计带有彩色图像的粗略深度图，并将其输出到下一个模块中，以进行逐步精确的细化。它可以简化估计大尺寸深度图的难度，并减少模糊问题。实验表明，该方法能够不断提高大型物体表面深度图的质量，并保持边缘清晰。我们提出的方法在KITTI数据集上执行高质量的深度估计，并在Make3D数据集上实现了很强的概括性。此外，它可以灵活地用于手机捕获的真实场景，而无需额外的培训。我们提出的方法在KITTI数据集上执行高质量的深度估计，并在Make3D数据集上实现了很强的概括性。此外，它可以灵活地用于手机捕获的真实场景，而无需额外的培训。我们提出的方法在KITTI数据集上执行高质量的深度估计，并在Make3D数据集上实现了很强的概括性。此外，它可以灵活地用于手机捕获的真实场景，而无需额外的培训。