Self-supervised Monocular Depth Estimation with Large Kernel Attention
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929516199280640 |
|---|---|
| author | Xiang, Xuezhi Wang, Yao Zhang, Lei Ombati, Denis Himu, Himaloy Zhen, Xiantong |
| author_facet | Xiang, Xuezhi Wang, Yao Zhang, Lei Ombati, Denis Himu, Himaloy Zhen, Xiantong |
| contents | Self-supervised monocular depth estimation has emerged as a promising approach since it does not rely on labeled training data. Most methods combine convolution and Transformer to model long-distance dependencies to estimate depth accurately. However, Transformer treats 2D image features as 1D sequences, and positional encoding somewhat mitigates the loss of spatial information between different feature blocks, tending to overlook channel features, which limit the performance of depth estimation. In this paper, we propose a self-supervised monocular depth estimation network to get finer details. Specifically, we propose a decoder based on large kernel attention, which can model long-distance dependencies without compromising the two-dimension structure of features while maintaining feature channel adaptivity. In addition, we introduce a up-sampling module to accurately recover the fine details in the depth map. Our method achieves competitive results on the KITTI dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_17895 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Self-supervised Monocular Depth Estimation with Large Kernel Attention Xiang, Xuezhi Wang, Yao Zhang, Lei Ombati, Denis Himu, Himaloy Zhen, Xiantong Computer Vision and Pattern Recognition Self-supervised monocular depth estimation has emerged as a promising approach since it does not rely on labeled training data. Most methods combine convolution and Transformer to model long-distance dependencies to estimate depth accurately. However, Transformer treats 2D image features as 1D sequences, and positional encoding somewhat mitigates the loss of spatial information between different feature blocks, tending to overlook channel features, which limit the performance of depth estimation. In this paper, we propose a self-supervised monocular depth estimation network to get finer details. Specifically, we propose a decoder based on large kernel attention, which can model long-distance dependencies without compromising the two-dimension structure of features while maintaining feature channel adaptivity. In addition, we introduce a up-sampling module to accurately recover the fine details in the depth map. Our method achieves competitive results on the KITTI dataset. |
| title | Self-supervised Monocular Depth Estimation with Large Kernel Attention |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.17895 |