AI
Enhancing Photogrammetric Digital Surface Models with Pretrained Diffusion Models and Multimodal Conditioning
Publication: Hugging Face Daily Papers
Author: Not available in collected metadata
Source published: 24/09/2026, 20:00:00 UTC
Briefing created: 28/09/2026, 09:32:57 UTC
Based on a feed excerpt; full article content has not been acquired. Source evidence retrieved 28/09/2026, 09:18:24 UTC.
Briefings
This study introduces a modified Stable Diffusion 3 architecture using photogrammetric DSMs and Pléiades imagery to refine 3D maps. Experiments in French cities show multimodal conditioning reduces Dense Urban RMSE from 6.00 to 3.45 m in in-context cities and from 4.16 to 2.77 m in the held-out city of Bordeaux. The method uses a pruned text stream and patch-wise normalization for stable training on LiDAR data.
Key points
- The study introduces a modified Stable Diffusion 3 architecture with a pruned text stream and patch-wise normalization to refine 3D maps using photogrammetric DSMs and Pléiades imagery.
- Experiments in French cities demonstrate that multimodal conditioning reduces Dense Urban RMSE from 6.00 to 3.45 m in in-context cities and from 4.16 to 2.77 m in the held-out city of Bordeaux.
Context and limitations
Results are limited to French cities; specific model architecture details and training parameters are not fully disclosed.
Generated by Bittrees-hosted qwen35-2b sha256:aaf42c8b7c3c on 28/09/2026, 09:32:57 UTC. Based on publisher-provided feed evidence; may not cover the full original article. Check the source for details.
View archived briefing on IPFS
bafybeiao25tl7g4zbdv4d7qxbm43w6iv2uoxpcg64uzqsajbclavduqd7q