Antoine Lorentz
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Antoine Lorentz has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Bastien Nespoulous
Thales, 92098 Paris, France
1 shared publication - Dawa Derksen
Centre National d’Etudes Spatiales (CNES), 75039 Paris, France
1 shared publication - Stéphane May
Centre National d' Études Spatiales (CNES) Toulouse France
1 shared publication - Valentine Bellet
Centre National d’Etudes Spatiales (CNES), 18 avenue Edouard Belin, Toulouse, France
1 shared publication
Latest Publications
- Open Access
- 24 September 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (19) , 3303
Enhancing Photogrammetric Digital Surface Models with Pretrained Diffusion Models and Multimodal Conditioning
Large-scale Digital Surface Models (DSMs) can be produced cost-effectively from satellite images via stereo-photogrammetry. However, the resulting 3D maps are often contaminated by noise, outliers, and voids. On the other hand, aerial LiDAR provides high-accuracy elevation measurements at a substantially higher cost. In this work, we study diffusion models conditioned both on photogrammetric DSMs and Pléiades imagery to refine vertically co-registered DSMs. We introduce a modified Stable Diffusion 3 architecture with a pruned text stream and a patch-wise normalization strategy, enabling stable training on LiDAR data and transfer from natural images to elevation maps. Experiments in French cities demonstrate that multimodal conditioning improves elevation accuracy, reducing Dense Urban RMSE from 6.00 to 3.45 m in the in-context cities and from 4.16 to 2.77 m in the held-out city of Bordeaux.
- 24 September 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (19) , 3303
Open AccessEnhancing Photogrammetric Digital Surface Models with Pretrained Diffusion Models and Multimodal Conditioning
Large-scale Digital Surface Models (DSMs) can be produced cost-effectively from satellite images via stereo-photogrammetry. However, the resulting 3D maps are often contaminated by noise, outliers, and voids. On the other hand, aerial LiDAR provides high-accuracy elevation measurements at a substantially higher cost. In this work, we study diffusion models conditioned both on photogrammetric DSMs and Pléiades imagery to refine vertically co-registered DSMs. We introduce a modified Stable Diffusion 3 architecture with a pruned text stream and a patch-wise normalization strategy, enabling stable training on LiDAR data and transfer from natural images to elevation maps. Experiments in French cities demonstrate that multimodal conditioning improves elevation accuracy, reducing Dense Urban RMSE from 6.00 to 3.45 m in the in-context cities and from 4.16 to 2.77 m in the held-out city of Bordeaux.