We propose an encoder–decoder CNN framework to predict depth from one single image in a self-supervised manner. To this aim, we design three kinds of encoder based on the recent advanced deep neural network and one kind of decoder which can generate multiscale predictions. Eight loss functions are designed based on the proposed encoder–decoder CNN framework to validate the performance. For training, we take rectified stereo image pairs as input of the CNN, which is trained by reconstructing image via learning multiscale disparity maps. For testing, the CNN can estimate the accurate depth information by inputting only one single image. We validate our framework on two public datasets in contrast to the state-of-the-art methods and our designed different variants, and the performance of different encoder–decoder architectures and loss functions is evaluated to obtain the best combination, which proves that our proposed method performs very well for single-image depth estimation without the supervision of ground truth.

中文翻译：

---

一种基于最大池化层前馈信息的单幅图像深度估计的自监督方法

我们提出了一种编码器 - 解码器 CNN 框架，以自监督的方式预测单个图像的深度。为此，我们基于最近先进的深度神经网络设计了三种编码器和一种可以生成多尺度预测的解码器。基于所提出的编码器-解码器 CNN 框架设计了八个损失函数来验证性能。对于训练，我们将校正后的立体图像对作为 CNN 的输入，通过学习多尺度视差图重建图像来训练 CNN。对于测试，CNN 可以通过仅输入一张单张图像来估计准确的深度信息。与最先进的方法和我们设计的不同变体相比，我们在两个公共数据集上验证了我们的框架，