Satellite Image Generation on Git-Rand 15k
9.25FIDTerraDiT-Ω-XL
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| TerraDiT-Ω-XLCondition=T + Ω + L, Zero-shot=true2026.06 | 9.25 | 0.3438 | — | — | 4.38 | |
| TerraDiT-Ω-XLCondition=T + B + L, Zero-shot=true2026.06 | 9.72 | 0.3509 | — | — | 4.45 | |
| TerraDiT-Ω-XLCondition=T + P + L, Zero-shot=true2026.06 | 9.91 | 0.3612 | — | — | 4.63 | |
| GeoDiT-XL/2-ΣCondition=T + P + L2026.03 | 12.01 | 0.3779 | 0.274 | 0.2877 | — | |
| TerraDiT-Σ-XLCondition=T + P + L, Zero-shot=true2026.06 | 12.01 | 0.3779 | — | — | 5.09 | |
| GeoDiT-XL/2-αCondition=T2026.03 | 14.21 | 0.3972 | 0.2599 | 0.2787 | — | |
| TerraDiT-α-XLCondition=T, Zero-shot=true2026.06 | 14.21 | 0.3972 | — | — | 5.13 | |
| Text2Earth*Condition=T2026.03 | 25.93 | 0.4269 | 0.2371 | 0.2871 | — | |
| Text2Earth*Condition=T, Zero-shot=true2026.06 | 25.93 | 0.4269 | — | — | 5.09 | |
| GeoSynthCondition=T2026.03 | 45.59 | 0.5413 | 0.1973 | 0.2478 | — | |
| GeoSynthCondition=T, Zero-shot=true2026.06 | 45.59 | 0.5413 | — | — | 18.88 | |
| GeoSynth-OSMCondition=T + O2026.03 | 53.88 | 0.4298 | 0.1979 | 0.2629 | — | |
| GeoSynth-OSMCondition=T + O, Zero-shot=true2026.06 | 53.88 | 0.4298 | — | — | 18.69 | |
| GLIGENCondition=T + B, Zero-shot=true2026.06 | 54 | 0.4792 | — | — | 10.82 | |
| CRS-DiffCondition=T2026.03 | 58.13 | 0.4758 | 0.1855 | 0.2798 | — | |
| CRS-DiffCondition=T, Zero-shot=true2026.06 | 58.13 | 0.4758 | — | — | 6.62 | |
| DiffusionSatCondition=T + L2026.03 | 71.55 | 0.5449 | 0.1615 | 0.2597 | — | |
| DiffusionSatCondition=T + L, Zero-shot=true2026.06 | 71.55 | 0.5449 | — | — | 19.22 | |
| PixArt-Σ-XL/2Condition=T2026.03 | 79.36 | 0.4954 | 0.1574 | 0.2535 | — | |
| PixArt-Σ-XLCondition=T, Zero-shot=true2026.06 | 79.36 | 0.4954 | — | — | 17.67 | |
| PixArt-α-XL/2Condition=T2026.03 | 85.82 | 0.522 | 0.1175 | 0.2509 | — | |
| PixArt-α-XLCondition=T, Zero-shot=true2026.06 | 85.82 | 0.522 | — | — | 16.3 | |
| AeroGenCondition=T + B, Zero-shot=true2026.06 | 85.96 | 0.5225 | — | — | 14.96 | |
| SD 3Condition=T2026.03 | 90.45 | 0.5083 | 0.1598 | 0.2567 | — | |
| SD 3Condition=T, Zero-shot=true2026.06 | 90.45 | 0.5083 | — | — | 14.21 | |
| InstanceDiffusionCondition=T + B, Zero-shot=true2026.06 | 94.18 | 0.5975 | — | — | 22.6 | |
| VectorSynthCondition=T + O, Zero-shot=true2026.06 | 95.15 | 0.4441 | — | — | 35.49 | |
| GeoRSSDCondition=T2026.03 | 129.23 | 0.5378 | 0.178 | 0.2692 | — | |
| GeoRSSDCondition=T, Zero-shot=true2026.06 | 129.23 | 0.5378 | — | — | 34.39 | |
| SDXLCondition=T2026.03 | 150.1 | 0.5929 | 0.1817 | 0.2423 | — | |
| SDXLCondition=T, Zero-shot=true2026.06 | 150.1 | 0.5929 | — | — | 21.27 | |
| VQGANCondition=T2026.03 | 171.37 | 0.4992 | 0.1482 | 0.217 | — | |
| MHN-VQGANCondition=T, Zero-shot=true2026.06 | 171.37 | 0.4992 | — | — | 26.56 | |
| VQVAECondition=T2026.03 | 188.46 | 0.5878 | 0.1729 | 0.2451 | — | |
| MHN-VQVAECondition=T, Zero-shot=true2026.06 | 188.46 | 0.5878 | — | — | 43.43 | |
| AeroGenCondition=T + B, Training Set=DIOR/-R, Images=45K, Params=907M2026.06 | — | — | 0.2049 | 0.2153 | — | |
| CRS-DiffCondition=T, Training Set=RSICD/fMoW/MillionAID, Images=1.1M, Params=860M2026.06 | — | — | 0.1855 | 0.2798 | — | |
| DiffusionSatCondition=T + L, Training Set=fMoW/Satlas/SpaceNet, Images=2M, Params=880M2026.06 | — | — | 0.1615 | 0.2597 | — | |
| GeoRSSDCondition=T, Training Set=RS5M, Images=5M, Params=866M2026.06 | — | — | 0.178 | 0.2692 | — | |
| GeoSynthCondition=T, Training Set=Internal, Images=45K, Params=866M2026.06 | — | — | 0.1973 | 0.2478 | — | |
| GeoSynth-OSMCondition=T + O, Training Set=Internal, Images=45K, Params=1.23B2026.06 | — | — | 0.1979 | 0.2629 | — | |
| GLIGENCondition=T + B, Training Set=LVIS/GoldG/O365/SBU/CC3M, Images=7M, Params=1.07B2026.06 | — | — | 0.1658 | 0.2703 | — | |
| InstanceDiffusionCondition=T + B, Training Set=Internal, Images=5M, Params=1.23B2026.06 | — | — | 0.0957 | 0.2063 | — | |
| MHN-VQGANCondition=T, Training Set=RSICD, Images=9K, Params=116M2026.06 | — | — | 0.1482 | 0.217 | — | |
| MHN-VQVAECondition=T, Training Set=RSICD, Images=9K, Params=29M2026.06 | — | — | 0.1729 | 0.2451 | — | |
| PixArt-α-XLCondition=T, Training Set=ImageNet/SAM/Internal, Images=25M, Params=611M2026.06 | — | — | 0.1175 | 0.2509 | — | |
| PixArt-Σ-XLCondition=T, Training Set=Internal, Images=33M, Params=611M2026.06 | — | — | 0.1574 | 0.2535 | — | |
| SD 3Condition=T, Training Set=Internal, Images=N/A, Params=2B2026.06 | — | — | 0.1598 | 0.2567 | — | |
| SDXLCondition=T, Training Set=Internal, Images=N/A, Params=2.6B2026.06 | — | — | 0.1817 | 0.2423 | — | |
| TerraDiT-α-XLCondition=T, Training Set=Git-10M, Images=2M, Params=836M2026.06 | — | — | 0.2599 | 0.2787 | — | |
| TerraDiT-Σ-XLCondition=T + P + L, Training Set=Git-10M/OSM, Images=2M, Params=1.12B2026.06 | — | — | 0.274 | 0.2877 | — | |
| TerraDiT-Ω-XLCondition=T + P + L, Training Set=Git-10M/OSM, Images=2M, Params=1.18B2026.06 | — | — | 0.2574 | 0.2804 | — | |
| TerraDiT-Ω-XLCondition=T + B + L, Training Set=Git-10M/OSM, Images=2M, Params=1.18B2026.06 | — | — | 0.2623 | 0.2813 | — | |
| TerraDiT-Ω-XLCondition=T + Ω + L, Training Set=Git-10M/OSM, Images=2M, Params=1.18B2026.06 | — | — | 0.2665 | 0.2812 | — | |
| Text2Earth*Condition=T, Training Set=Git-10M, Images=10M, Params=867M2026.06 | — | — | 0.2371 | 0.2871 | — | |
| VectorSynthCondition=T + O, Training Set=OSM-Polygon, Images=20K, Params=1.23B2026.06 | — | — | 0.1711 | 0.2763 | — |