129 / 2022-10-22 20:58:05

Ghost-Depth:A Lightweight Encoder-Decoder Network for Monocular Depth estimation

In recent years, convolutional neural networks especially those based on encoder-decoder architecture have been used in the task of monocular depth estimation, and it has brought great success. However, the parameters and computational cost of networks are increasing constantly so as to improve predicting accuracy. In view of this situation, a network model based on a lightweight encoder-decoder structure is designed to estimate monocular depth in this paper, which has good accuracy and reduces the number of parameters. In order to design a lightweight network, a lightweight network named GhostNet was chose when encoding. In the upsampling process in decoder, Ghost convolution with fewer parameters was used instead of conventional convolutions. And a lightweight attentional feature fusion module was combined with traditional skip connections when upsampling. It compensated for the loss of detail information in feature maps due to downsampling, and further improved the model accuracy. Experiments on dataset NYU-Depth V2 demonstrate that the number of parameters is 2.7M and the accuracy is 79.7%. Our proposed method is lightweight and efficient and outperforms most lightweight methods.