Monocular depth estimation is a popular research topic in the field of autonomous driving. Nowadays many models are leading in accuracy but performing poorly in a real-time scenario. To effectively increase the depth estimation efficiency, we propose a novel model combining a multi-scale pyramid architecture for depth estimation together with adaptive receptive fields. The pyramid architecture reduces the trainable parameters from dozens of mega to less than 10 mega. Adaptive receptive fields are more sensitive to objects at different depth/distances in images, leading to better accuracy. We have adopted stacked convolution kernels instead of raw kernels to compress the model. Thus, the model that we proposed performs well in both real-time performance and estimation accuracy. We provide a set of experiments where our model performs better in terms of Eigen split than other previously known models. Furthermore, we show that our model is also better in runtime performance in regard to the depth estimation to the rest of models but the Pyd-Net model. Finally, our model is a lightweight depth estimation model with state-of-the-art accuracy.

单眼深度估计是自动驾驶领域的热门研究主题。如今，许多模型在精度上都处于领先地位，但在实时场景中却表现不佳。为了有效地提高深度估计效率，我们提出了一种新颖的模型，该模型结合了用于深度估计的多尺度金字塔体系结构和自适应接收场。金字塔体系结构将可训练参数从几十兆降低到了不到十兆。自适应接收场对图像中不同深度/距离处的对象更敏感，从而导致更好的准确性。我们采用堆叠卷积核而不是原始核来压缩模型。因此，我们提出的模型在实时性能和估计精度上均表现良好。我们提供了一组实验，其中我们的模型在本征分裂方面比其他先前已知的模型表现更好。此外，我们证明，相对于除Pyd-Net模型之外的其余模型，深度模型的运行时性能也更好。最后，我们的模型是具有最先进准确性的轻量级深度估计模型。