Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.16362 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912970907320320 |
|---|---|
| author | Wang, Ruizhi Li, Weihan Feng, Zunlei Zhang, Haofei Song, Mingli Wang, Jiayu Song, Jie Sun, Li |
| author_facet | Wang, Ruizhi Li, Weihan Feng, Zunlei Zhang, Haofei Song, Mingli Wang, Jiayu Song, Jie Sun, Li |
| contents | Real-time, high-fidelity monocular depth estimation from remote sensing imagery is crucial for numerous applications, yet existing methods face a stark trade-off between accuracy and efficiency. Although using Vision Transformer (ViT) backbones for dense prediction is fast, they often exhibit poor perceptual quality. Conversely, diffusion models offer high fidelity but at a prohibitive computational cost. To overcome these limitations, we propose Depth Detail Diffusion for Remote Sensing Monocular Depth Estimation ($D^3$-RSMDE), an efficient framework designed to achieve an optimal balance between speed and quality. Our framework first leverages a ViT-based module to rapidly generate a high-quality preliminary depth map construction, which serves as a structural prior, effectively replacing the time-consuming initial structure generation stage of diffusion models. Based on this prior, we propose a Progressive Linear Blending Refinement (PLBR) strategy, which uses a lightweight U-Net to refine the details in only a few iterations. The entire refinement step operates efficiently in a compact latent space supported by a Variational Autoencoder (VAE). Extensive experiments demonstrate that $D^3$-RSMDE achieves a notable 11.85% reduction in the Learned Perceptual Image Patch Similarity (LPIPS) perceptual metric over leading models like Marigold, while also achieving over a 40x speedup in inference and maintaining VRAM usage comparable to lightweight ViT models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_16362 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | $D^3$-RSMDE: 40$\times$ Faster and High-Fidelity Remote Sensing Monocular Depth Estimation Wang, Ruizhi Li, Weihan Feng, Zunlei Zhang, Haofei Song, Mingli Wang, Jiayu Song, Jie Sun, Li Computer Vision and Pattern Recognition Artificial Intelligence Real-time, high-fidelity monocular depth estimation from remote sensing imagery is crucial for numerous applications, yet existing methods face a stark trade-off between accuracy and efficiency. Although using Vision Transformer (ViT) backbones for dense prediction is fast, they often exhibit poor perceptual quality. Conversely, diffusion models offer high fidelity but at a prohibitive computational cost. To overcome these limitations, we propose Depth Detail Diffusion for Remote Sensing Monocular Depth Estimation ($D^3$-RSMDE), an efficient framework designed to achieve an optimal balance between speed and quality. Our framework first leverages a ViT-based module to rapidly generate a high-quality preliminary depth map construction, which serves as a structural prior, effectively replacing the time-consuming initial structure generation stage of diffusion models. Based on this prior, we propose a Progressive Linear Blending Refinement (PLBR) strategy, which uses a lightweight U-Net to refine the details in only a few iterations. The entire refinement step operates efficiently in a compact latent space supported by a Variational Autoencoder (VAE). Extensive experiments demonstrate that $D^3$-RSMDE achieves a notable 11.85% reduction in the Learned Perceptual Image Patch Similarity (LPIPS) perceptual metric over leading models like Marigold, while also achieving over a 40x speedup in inference and maintaining VRAM usage comparable to lightweight ViT models. |
| title | $D^3$-RSMDE: 40$\times$ Faster and High-Fidelity Remote Sensing Monocular Depth Estimation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2603.16362 |