Sat3R: Satellite DSM Reconstruction via RPC-Aware Depth Fine-tuning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917471625150464 |
|---|---|
| author | Yang, Qiaoyi Zhou, Chaoyi Liu, Xi Wang, Run Xu, Minghui Pesé, Mert D. Luo, Feng Xu, Yuhao Cheng, Zhi-Qi Chen, Qiushi Qi, Hairong Huang, Siyu |
| author_facet | Yang, Qiaoyi Zhou, Chaoyi Liu, Xi Wang, Run Xu, Minghui Pesé, Mert D. Luo, Feng Xu, Yuhao Cheng, Zhi-Qi Chen, Qiushi Qi, Hairong Huang, Siyu |
| contents | Accurate Digital Surface Model (DSM) reconstruction from satellite imagery is critical for applications such as disaster response, urban planning, and large-scale geographic mapping. Existing approaches face a fundamental trade-off: optimization-based methods achieve strong accuracy but require hours of per-scene computation, while generalizable geometry foundation models offer near-instant inference but fail to generalize to satellite imagery due to the domain gap introduced by the Rational Polynomial Camera (RPC) model and mismatched depth scale distributions. We present Sat3R, a feed-forward framework that bridges this gap via RPC-aware metric depth fine-tuning of Depth Anything V2 using the Scale-Invariant Logarithmic (SiLog) loss. By constructing physically consistent pseudo depth supervision from RPC geometry, Sat3R adapts a monocular depth foundation model to the satellite domain without per-scene optimization. Experiments on the DFC2019 benchmark demonstrate that Sat3R reduces MAE by 38% over zero-shot feed-forward baselines and achieves competitive accuracy against optimization-based methods, while delivering over 300x speedup. Sat3R demonstrates that feed-forward models, when properly adapted to the satellite domain, can match optimization-based accuracy at a fraction of the computational cost, paving the way for practical large-scale satellite DSM reconstruction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_07264 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Sat3R: Satellite DSM Reconstruction via RPC-Aware Depth Fine-tuning Yang, Qiaoyi Zhou, Chaoyi Liu, Xi Wang, Run Xu, Minghui Pesé, Mert D. Luo, Feng Xu, Yuhao Cheng, Zhi-Qi Chen, Qiushi Qi, Hairong Huang, Siyu Computer Vision and Pattern Recognition Accurate Digital Surface Model (DSM) reconstruction from satellite imagery is critical for applications such as disaster response, urban planning, and large-scale geographic mapping. Existing approaches face a fundamental trade-off: optimization-based methods achieve strong accuracy but require hours of per-scene computation, while generalizable geometry foundation models offer near-instant inference but fail to generalize to satellite imagery due to the domain gap introduced by the Rational Polynomial Camera (RPC) model and mismatched depth scale distributions. We present Sat3R, a feed-forward framework that bridges this gap via RPC-aware metric depth fine-tuning of Depth Anything V2 using the Scale-Invariant Logarithmic (SiLog) loss. By constructing physically consistent pseudo depth supervision from RPC geometry, Sat3R adapts a monocular depth foundation model to the satellite domain without per-scene optimization. Experiments on the DFC2019 benchmark demonstrate that Sat3R reduces MAE by 38% over zero-shot feed-forward baselines and achieves competitive accuracy against optimization-based methods, while delivering over 300x speedup. Sat3R demonstrates that feed-forward models, when properly adapted to the satellite domain, can match optimization-based accuracy at a fraction of the computational cost, paving the way for practical large-scale satellite DSM reconstruction. |
| title | Sat3R: Satellite DSM Reconstruction via RPC-Aware Depth Fine-tuning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.07264 |