EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Geometry-Guided Diffusion SAR Point Cloud Denoising

Chengwei Zhang, Tao Jiang, Xinhao Xu, Wenjie Li, Fubo Zhang, Longyong Chen

Remote Sensing · 26.07.2026 · 18 (15) · 2458

DOI: 10.3390/rs18152458 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 26.07.2026. Verfasst von Chengwei Zhang und 5 weiteren Autor:innen. Die Arbeit nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Three-dimensional synthetic aperture radar (SAR) point clouds provide valuable geometric observations of urban scenes, but they often suffer from severe noise and layer-like artifacts caused by the low signal-to-noise ratio and tomographic imaging mechanism. These degradations make SAR point cloud denoising significantly more challenging than conventional LiDAR point cloud denoising. In this paper, we propose a Geometry-guided Diffusion SAR Point Cloud Denoising (GDSD) framework to recover geometrically coherent building surfaces from noisy SAR point clouds.The key idea is to exploit relatively clean LiDAR point clouds as geometry priors while avoiding the need for paired SAR–LiDAR supervision or clean SAR ground truth. Specifically, we introduce a Forward Gaussian Noising Process to disrupt the intrinsic layer-like artifacts of SAR point clouds and reduce the input-level discrepancy between SAR and LiDAR domains. We further design a geometry prototype-based alignment module that projects SAR and LiDAR bottleneck features into a shared LiDAR-dominated latent space, enabling geometry-aware conditional reverse diffusion. A DiT-3D-based denoising network is then trained with LiDAR-domain diffusion supervision and applied to SAR point clouds using the aligned SAR geometry condition. To evaluate the proposed method, we construct a SAR point cloud denoising benchmark based on the MV3DSAR dataset with CAD-derived reference surfaces. Experimental results show that GDSD significantly improves the quality of noisy SAR point clouds and clearly outperforms the previous conventional LiDAR point cloud denoising baseline, producing more continuous and geometrically coherent SAR building point clouds.

Förderung

  • National Key Research and Development Program of China

Zitieren

APA

Zhang, C., Jiang, T., Xu, X., Li, W., Zhang, F., & Chen, L. (2026). Geometry-Guided Diffusion SAR Point Cloud Denoising. Remote Sensing, 18(15), 2458. https://doi.org/10.3390/rs18152458

Vancouver

Zhang C, Jiang T, Xu X, Li W, Zhang F, Chen L. Geometry-Guided Diffusion SAR Point Cloud Denoising. Remote Sensing. 2026;18(15):2458. doi:10.3390/rs18152458

BibTeX
@article{Zhang2026,
  author = {Zhang, Chengwei and Jiang, Tao and Xu, Xinhao and Li, Wenjie and Zhang, Fubo and Chen, Longyong},
  title = {Geometry-Guided Diffusion SAR Point Cloud Denoising},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {15},
  pages = {2458},
  doi = {10.3390/rs18152458}
}
Kostenlos starten →