Research
The map is generated.
The measurement is not.
The goal is a realistic, plausible version of what the satellite saw — not a pixel-exact reconstruction, which the physics doesn't permit. Inventing plausible detail is the point; staying consistent with the source is the law.
System vision target architecture
- Multi-temporal LR acquisition — ten Sentinel-2 revisits per site
- Alignment — co-registration against the reference frame
- Modality set — spectral composites, OSM vectors, structure priors
- S — the positional representation of all modalities
- S + the date-matched LR condition two ControlNets in development
- Predicted HR → height estimation / 3D in development
ControlNet conditioning was tested and concluded negative in 2026-06 experiments; the redesign above is a target, not a shipped result — we say so here on purpose.
Shipping today validated
- Corpus: 730 co-registered S2↔aerial pairs, 7 granules, 10-frame temporal stacks
- S_struct — a 6-class structural map (roads, buildings, rail, water, vegetation, bare) + confidence
- Stage A — SEAN generator + OASIS discriminator GAN: 10 m → 2.5 m (×4), structure-conditioned
- Stage B — LoRA-adapted pixel diffusion texture decoder: 2.5 m → 0.5 m research-only · weights license
- Verification — round-trip to 10 m + texture statistics vs real-aerial banks, every output
Evaluation protocol
Pre-registered gates, anti-over-texture guards, an adversarial judge with its own published failure, and a human forced-choice test as the success criterion. Full yardstick with one-line explanations on the Evidence page; raw values in metrics.json.
Milestones
- 2026-06-16Slovenia S2↔DOF corpus v1 — grown to 730 co-registered pairs, ≈1,196 km²
- 2026-06-19ControlNet conditioning concluded NEGATIVE at both sites; pivot to the SEAN+OASIS GAN
- 2026-07-02Goal ratified: realistic-plausible over GT-exact; cascade beats the bicubic floor for the first time
- 2026-07-04Goal reorder: 2.5 m indistinguishability first; autonomous evaluation loop goes live
- 2026-07-05Goal-metric suite v2 frozen; 13 arms + 5 public external models scored on identical inputs
- 2026-07-06First human blind-test session logged (0.90 vs goal 0.50); conditioning-map rebuild becomes the active workstream
Negative results stay in the record — the ControlNet conclusion above is one of several we publish rather than bury.