MOMO

Analyzes Mars orbital imagery for craters, boulders, and surface landforms

Field
Planetary science
Method
Foundation model
Data it takes
imagery
License
MIT AND CC-BY-4.0

MOMO is a vision transformer pretrained on Mars orbital imagery from HiRISE, CTX and THEMIS. It supports crater segmentation, boulder detection, dust devil identification, and landform classification against the DoMars16k scheme.

Planetary surface analysis shares its methods with terrestrial remote sensing but almost none of its training data, which is why a Mars-specific pretrained backbone is required.

Upstream project →

Catalog entry last checked 2026-08-17. All models →

Run MOMO on your data

The lab runs this on its own compute, in a container, with the inputs and parameters recorded alongside the result. Initial scoping conversations are free.

Contact the Lab