Thales refines satellite DSMs with diffusion models, cutting urban RMSE from 6.00 to 3.45 m
thalesgroup · hf · 2026-09-28
Thales researchers present a modified Stable Diffusion 3 with a pruned text stream and patch-wise normalization to refine photogrammetric Digital Surface Models conditioned on both DSMs and Pléiades imagery. Trained against LiDAR ground truth, the approach cuts Dense Urban RMSE from 6.00 to 3.45 m in in-context French cities and from 4.16 to 2.77 m in held-out Bordeaux, offering a cheap path to accurate 3D elevation maps from satellite images.
More from Research
- Inference Engineering Archive launches: end-to-end resource from first principles to production — soham_btw · 2026-09-28
- OpenAI's thousands of agents solved Navier-Stokes; mathematicians worry brute force erases the art — nordicinst · 2026-09-28
- University of Tokyo grows self-healing living human skin on robotic finger — TinfoilTricorn · 2026-09-28
- Stanford's HomeBody gives frontier VLMs spatial memory and composable humanoid skills — CyberRobooo · 2026-09-28
- MOPD drops OPSD's self-teaching flaw, but naive multi-teacher averaging may distill style over capability — novasarc01 · 2026-09-28
- UK Startup Turns Gaming Inputs Into Training Data for World Models, With LeCun Advising — nordicinst · 2026-09-28