Monocular Depth Estimation with Global-Aware Discretization and Local Context Modeling
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912521071362048 |
|---|---|
| author | Wu, Heng Zhang, Qian Zhang, Guixu |
| author_facet | Wu, Heng Zhang, Qian Zhang, Guixu |
| contents | Accurate monocular depth estimation remains a challenging problem due to the inherent ambiguity that stems from the ill-posed nature of recovering 3D structure from a single view, where multiple plausible depth configurations can produce identical 2D projections. In this paper, we present a novel depth estimation method that combines both local and global cues to improve prediction accuracy. Specifically, we propose the Gated Large Kernel Attention Module (GLKAM) to effectively capture multi-scale local structural information by leveraging large kernel convolutions with a gated mechanism. To further enhance the global perception of the network, we introduce the Global Bin Prediction Module (GBPM), which estimates the global distribution of depth bins and provides structural guidance for depth regression. Extensive experiments on the NYU-V2 and KITTI dataset demonstrate that our method achieves competitive performance and outperforms existing approaches, validating the effectiveness of each proposed component. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_03186 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Monocular Depth Estimation with Global-Aware Discretization and Local Context Modeling Wu, Heng Zhang, Qian Zhang, Guixu Computer Vision and Pattern Recognition Accurate monocular depth estimation remains a challenging problem due to the inherent ambiguity that stems from the ill-posed nature of recovering 3D structure from a single view, where multiple plausible depth configurations can produce identical 2D projections. In this paper, we present a novel depth estimation method that combines both local and global cues to improve prediction accuracy. Specifically, we propose the Gated Large Kernel Attention Module (GLKAM) to effectively capture multi-scale local structural information by leveraging large kernel convolutions with a gated mechanism. To further enhance the global perception of the network, we introduce the Global Bin Prediction Module (GBPM), which estimates the global distribution of depth bins and provides structural guidance for depth regression. Extensive experiments on the NYU-V2 and KITTI dataset demonstrate that our method achieves competitive performance and outperforms existing approaches, validating the effectiveness of each proposed component. |
| title | Monocular Depth Estimation with Global-Aware Discretization and Local Context Modeling |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.03186 |