geospatial
MegaLoc
Image retrieval model for visual place recognition and localisation across many settings.
Levelmodel
Classgeospatial
Parameters228.64M
Contextnot in the notes
Released24 Feb 2025
Opennessopen weights permissive
Runs onnot in the notes
Statusactive
Identity
- Developer
- Polytechnic University of Turin
- Family
- not in the notes
- Released
- 24 Feb 2025 sourcesannouncement page
- Weights published
- 27 Feb 2025
- Record checked
- 12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- dense transformer
- Total parameters
- 228.64M sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- not in the notes
- Input
- image
- Output
- labels and boxes
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open weights permissive
- Licence
- MIT License sources
- Access routes
- open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- not in the notes
- Footprint
- not in the notes
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Benchmark Results
The notes record no benchmark result for this model.
Lineage
The notes record no lineage for this model.
Industry Use Cases
No industry use case links this model.
Links
ModelMegaLocPolytechnic University of Turin, geospatial
MegaLocPolytechnic University of Turin, geospatialUse Casesnone recorded
Who Runs Itnone recorded
Organisations 1
Sources
- arxiv.org/abs/2502.17237 https://arxiv.org/abs/2502.17237
- huggingface.co/gberton/MegaLoc https://huggingface.co/gberton/MegaLoc
- huggingface.co/api/models?pipeline_tag=image-feature-extract... https://huggingface.co/api/models?pipeline_tag=image-feature-extraction&sort=downloads&limit=50
- arxiv.org/html/2502.17237 https://arxiv.org/html/2502.17237
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "MegaLoc", https://aurion.semai.id/models/megaloc/, records of October 2026.