Self-Supervised Monocular Depth Estimation Based on Channel Attention
Scene structure and local details are important factors in producing high-quality depth estimations so as to solve fuzzy artifacts in depth prediction results. We propose a new network structure that combines two channel attention modules in a deep prediction network. The structure perception module...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Photonics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2304-6732/9/6/434 |
| Summary: | Scene structure and local details are important factors in producing high-quality depth estimations so as to solve fuzzy artifacts in depth prediction results. We propose a new network structure that combines two channel attention modules in a deep prediction network. The structure perception module (spm) uses a frequency channel attention network. We use frequencies from different perspectives to analyze the channel representation as a compression process. This enhances the perception of the scene structure and obtains more feature information. The detail emphasis module (dem) adopts the global attention mechanism. It improves the performance of deep neural networks by reducing irrelevant information and magnifying global interactive representations. Emphasizing important details effectively fuses features at different scales to achieve more accurate and clearer depth predictions. Experiments show that our network produces clearer depth estimations, and our accuracy rate on the KITTI benchmark has improved from 98.1% to 98.3% in the δ < 1.25<sup>3</sup> metric. |
|---|---|
| ISSN: | 2304-6732 |