Neurocomputing | 2021
RDRF-Net: A pyramid architecture network with residual-based dynamic receptive fields for unsupervised depth estimation
Abstract
Abstract Image depth estimation is a challenging problem in computer vision, especially considering both high accuracy and low run time. To save run time and maintain high accuracy, we present a new lightweight model in this paper, i.e., a Residual-based Dynamic Receptive Field Network (RDRF-Net) . This model can automatically select the receptive fields suitable for different image scales to generate the depth maps with higher fitting degrees. Residual design and bottleneck layers are used to compress the network for reducing run time. Three groups of experiments are performed on the KITTI dataset to test the accuracy, computation time, and the impact of dynamic receptive fields. Experimental results show that RDRF-Net has comparable accuracy with Godard’s model and significantly outperforms it in terms of run time. In addition, it performs closely to Pyd-Net in terms of run time and beats Pyd-Net’s accuracy. Experiments also demonstrate the beneficial impact of dynamic receptive fields on improving depth estimation accuracy.