Aerial Multi-View Stereo via Adaptive Depth Range Inference and Normal Cues
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910991716974592 |
|---|---|
| author | Liu, Yimei Ju, Yakun Rao, Yuan Fan, Hao Dong, Junyu Gao, Feng Du, Qian |
| author_facet | Liu, Yimei Ju, Yakun Rao, Yuan Fan, Hao Dong, Junyu Gao, Feng Du, Qian |
| contents | Three-dimensional digital urban reconstruction from multi-view aerial images is a critical application where deep multi-view stereo (MVS) methods outperform traditional techniques. However, existing methods commonly overlook the key differences between aerial and close-range settings, such as varying depth ranges along epipolar lines and insensitive feature-matching associated with low-detailed aerial images. To address these issues, we propose an Adaptive Depth Range MVS (ADR-MVS), which integrates monocular geometric cues to improve multi-view depth estimation accuracy. The key component of ADR-MVS is the depth range predictor, which generates adaptive range maps from depth and normal estimates using cross-attention discrepancy learning. In the first stage, the range map derived from monocular cues breaks through predefined depth boundaries, improving feature-matching discriminability and mitigating convergence to local optima. In later stages, the inferred range maps are progressively narrowed, ultimately aligning with the cascaded MVS framework for precise depth regression. Moreover, a normal-guided cost aggregation operation is specially devised for aerial stereo images to improve geometric awareness within the cost volume. Finally, we introduce a normal-guided depth refinement module that surpasses existing RGB-guided techniques. Experimental results demonstrate that ADR-MVS achieves state-of-the-art performance on the WHU, LuoJia-MVS, and München datasets, while exhibits superior computational complexity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_05655 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Aerial Multi-View Stereo via Adaptive Depth Range Inference and Normal Cues Liu, Yimei Ju, Yakun Rao, Yuan Fan, Hao Dong, Junyu Gao, Feng Du, Qian Computer Vision and Pattern Recognition Image and Video Processing Three-dimensional digital urban reconstruction from multi-view aerial images is a critical application where deep multi-view stereo (MVS) methods outperform traditional techniques. However, existing methods commonly overlook the key differences between aerial and close-range settings, such as varying depth ranges along epipolar lines and insensitive feature-matching associated with low-detailed aerial images. To address these issues, we propose an Adaptive Depth Range MVS (ADR-MVS), which integrates monocular geometric cues to improve multi-view depth estimation accuracy. The key component of ADR-MVS is the depth range predictor, which generates adaptive range maps from depth and normal estimates using cross-attention discrepancy learning. In the first stage, the range map derived from monocular cues breaks through predefined depth boundaries, improving feature-matching discriminability and mitigating convergence to local optima. In later stages, the inferred range maps are progressively narrowed, ultimately aligning with the cascaded MVS framework for precise depth regression. Moreover, a normal-guided cost aggregation operation is specially devised for aerial stereo images to improve geometric awareness within the cost volume. Finally, we introduce a normal-guided depth refinement module that surpasses existing RGB-guided techniques. Experimental results demonstrate that ADR-MVS achieves state-of-the-art performance on the WHU, LuoJia-MVS, and München datasets, while exhibits superior computational complexity. |
| title | Aerial Multi-View Stereo via Adaptive Depth Range Inference and Normal Cues |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2506.05655 |