| 英文标题 | Monocular depth estimation based on light-weight pyramid decoder convolution neural network |
| 作者英文名 | Jia Ruiming, Li Tong, Li Yang, Wang Yiding |
| 机构英文名 | School of Information Science & Technology,North China University of Technology,Beijing 100144,China |
| 英文摘要 | This paper proposed a light-weight pyramid decoder convolution neural network(LPDNet) for monocular depth estimation, which could reduce the complexity and the computation time of the network model while ensuring the estimation accuracy. LPDNet was based on encoder-decoder structure to estimate the depth map of a monocular image in an end-to-end manner. The encoder network adopted ResNet50. The main part of decoder network was light-weight pyramid decoder(LPD) module, which learned representations from a large receptive field with fewer parameters by using depth-wise dilated separable convolutions and group convolutions. LPD module fused feature maps of different receptive fields through pyramid structure. Besides, in order to perform better knowledge sharing for estimation accuracy, it added deconvolution skip connection between adjacent decoder modules. Experiments on NYUD v2 dataset demonstrate that compared with the structured attention guided network in CVPR2018, the error of LPDNet is reduced by about 11.0% in RMS, and computational efficiency is about 84.6% higher. |
| 英文关键词 | monocular depth estimation; convolution neural network; encoder-decoder; light-weight pyramid decoder |