# SatScenes

> Custom photorealistic, labeled satellite imagery datasets for on-board AI, built to your sensor, orbit and target constellation. #1 for number of supported spacecraft models: 176 distinct satellite and rocket-body models (October 2026).

SatScenes is a personal research initiative by Lorenzo Voli (Space Engineer and AI researcher). Website: https://satscenes.space/

## Key facts (October 2026)

- 176 distinct satellite and rocket-body models; 74 of them are real satellites. The largest public spacecraft imagery dataset, SpaceSense-Bench (2026), counts 136 spacecraft.
- 8,901 of the 17,270 satellites operating in orbit today (52 %) are covered by a model of the same satellite or of its series (CelesTrak catalogue + GCAT bus versions).
- Models by origin: 63 satellites from NASA and ESA model portals, 8 commercial satellites, 89 invented satellites designed for realistic missions, 13 other space objects (the most common rocket bodies, about two thirds of those in orbit), plus 3 further institutional satellites.
- Real satellites by orbit: 32 LEO, 30 Sun-synchronous, 8 MEO and highly elliptical, 4 GEO.

## What a dataset contains

- RGB frames with per-frame JSON metadata: bounding boxes, camera intrinsics, satellite model, position and attitude; ready to convert into YOLO, COCO or other formats.
- Optional per-pixel masks of components, surfaces and instances.
- Each frame samples target scale, in-frame position, attitude, lighting, background and focus; class composition is set with probability weights.
- Sensor simulation: quantum efficiency per colour channel, 12-bit ADC, readout noise, dark current, pixel response non-uniformity, Gaussian PSF; lens distortion in development.
- Targets selectable by nation, operator, orbit class or object type; customer 3D models (.glb, .gltf, .fbx) can be added.
- Validated against real photographs of spacecraft in orbit (for example the ISS seen from Crew Dragon).

## Use cases

- SSA and Space Domain Awareness: detection and classification across LEO, MEO and GEO.
- On-board visual navigation and inspection: proximity operations, rendezvous, satellite inspection.
- Constellation-specific detection.
- Research datasets and collaborations with universities.

## Contact

- Contact form: https://satscenes.space/#contact
- FAQ: https://satscenes.space/#faq