RDRF-Net: A pyramid architecture network with residual-based dynamic receptive fields for unsupervised depth estimation
- Publisher:
- Elsevier BV
- Publication Type:
- Journal Article
- Citation:
- Neurocomputing, 2021, 457, pp. 1-12
- Issue Date:
- 2021-10-07
Closed Access
| Filename | Description | Size | |||
|---|---|---|---|---|---|
| 1-s2.0-S0925231221008523-main.pdf | Published version | 2.24 MB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
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 light-weight 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.
Please use this identifier to cite or link to this item: