Pyramid Feature Attention Network for Monocular Depth Prediction
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917603006480384 |
|---|---|
| author | Xu, Yifang Peng, Chenglei Li, Ming Li, Yang Du, Sidan |
| author_facet | Xu, Yifang Peng, Chenglei Li, Ming Li, Yang Du, Sidan |
| contents | Deep convolutional neural networks (DCNNs) have achieved great success in monocular depth estimation (MDE). However, few existing works take the contributions for MDE of different levels feature maps into account, leading to inaccurate spatial layout, ambiguous boundaries and discontinuous object surface in the prediction. To better tackle these problems, we propose a Pyramid Feature Attention Network (PFANet) to improve the high-level context features and low-level spatial features. In the proposed PFANet, we design a Dual-scale Channel Attention Module (DCAM) to employ channel attention in different scales, which aggregate global context and local information from the high-level feature maps. To exploit the spatial relationship of visual features, we design a Spatial Pyramid Attention Module (SPAM) which can guide the network attention to multi-scale detailed information in the low-level feature maps. Finally, we introduce scale-invariant gradient loss to increase the penalty on errors in depth-wise discontinuous regions. Experimental results show that our method outperforms state-of-the-art methods on the KITTI dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_01440 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Pyramid Feature Attention Network for Monocular Depth Prediction Xu, Yifang Peng, Chenglei Li, Ming Li, Yang Du, Sidan Computer Vision and Pattern Recognition Deep convolutional neural networks (DCNNs) have achieved great success in monocular depth estimation (MDE). However, few existing works take the contributions for MDE of different levels feature maps into account, leading to inaccurate spatial layout, ambiguous boundaries and discontinuous object surface in the prediction. To better tackle these problems, we propose a Pyramid Feature Attention Network (PFANet) to improve the high-level context features and low-level spatial features. In the proposed PFANet, we design a Dual-scale Channel Attention Module (DCAM) to employ channel attention in different scales, which aggregate global context and local information from the high-level feature maps. To exploit the spatial relationship of visual features, we design a Spatial Pyramid Attention Module (SPAM) which can guide the network attention to multi-scale detailed information in the low-level feature maps. Finally, we introduce scale-invariant gradient loss to increase the penalty on errors in depth-wise discontinuous regions. Experimental results show that our method outperforms state-of-the-art methods on the KITTI dataset. |
| title | Pyramid Feature Attention Network for Monocular Depth Prediction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.01440 |