Multi-view 3D surface reconstruction from SAR images by inverse rendering
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929715936231424 |
|---|---|
| author | Barbier--Renard, Emile Tupin, Florence Trouvé, Nicolas Denis, Loïc |
| author_facet | Barbier--Renard, Emile Tupin, Florence Trouvé, Nicolas Denis, Loïc |
| contents | 3D reconstruction of a scene from Synthetic Aperture Radar (SAR) images mainly relies on interferometric measurements, which involve strict constraints on the acquisition process. These last years, progress in deep learning has significantly advanced 3D reconstruction from multiple views in optical imaging, mainly through reconstruction-by-synthesis approaches pioneered by Neural Radiance Fields. In this paper, we propose a new inverse rendering method for 3D reconstruction from unconstrained SAR images, drawing inspiration from optical approaches. First, we introduce a new simplified differentiable SAR rendering model, able to synthesize images from a digital elevation model and a radar backscattering coefficients map. Then, we introduce a coarse-to-fine strategy to train a Multi-Layer Perceptron (MLP) to fit the height and appearance of a given radar scene from a few SAR views. Finally, we demonstrate the surface reconstruction capabilities of our method on synthetic SAR images produced by ONERA's physically-based EMPRISE simulator. Our method showcases the potential of exploiting geometric disparities in SAR images and paves the way for multi-sensor data fusion. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_10492 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multi-view 3D surface reconstruction from SAR images by inverse rendering Barbier--Renard, Emile Tupin, Florence Trouvé, Nicolas Denis, Loïc Computer Vision and Pattern Recognition Signal Processing 3D reconstruction of a scene from Synthetic Aperture Radar (SAR) images mainly relies on interferometric measurements, which involve strict constraints on the acquisition process. These last years, progress in deep learning has significantly advanced 3D reconstruction from multiple views in optical imaging, mainly through reconstruction-by-synthesis approaches pioneered by Neural Radiance Fields. In this paper, we propose a new inverse rendering method for 3D reconstruction from unconstrained SAR images, drawing inspiration from optical approaches. First, we introduce a new simplified differentiable SAR rendering model, able to synthesize images from a digital elevation model and a radar backscattering coefficients map. Then, we introduce a coarse-to-fine strategy to train a Multi-Layer Perceptron (MLP) to fit the height and appearance of a given radar scene from a few SAR views. Finally, we demonstrate the surface reconstruction capabilities of our method on synthetic SAR images produced by ONERA's physically-based EMPRISE simulator. Our method showcases the potential of exploiting geometric disparities in SAR images and paves the way for multi-sensor data fusion. |
| title | Multi-view 3D surface reconstruction from SAR images by inverse rendering |
| topic | Computer Vision and Pattern Recognition Signal Processing |
| url | https://arxiv.org/abs/2502.10492 |