ucam-eo/tessera
[CVPR26] TESSERA is a foundation model that can process time-series satellite imagery for applications such as land classification and canopy height prediction. Developed at the University of Cambridge, it enables efficient extraction of temporal patterns from Earth observation
TESSERA helps scientists and environmental analysts extract meaningful insights from vast amounts of satellite imagery, even when data is incomplete due to clouds. It takes raw time-series satellite data and outputs dense, 128-dimensional representations (embeddings) for every 10-meter pixel globally. This allows users to perform tasks like land classification, carbon accounting, and monitoring ecosystem changes more efficiently.
498 stars.
Use this if you need to analyze global, high-resolution satellite imagery time series for environmental monitoring or land use applications, especially when dealing with gaps caused by cloud cover.
Not ideal if your primary need is real-time processing of live satellite feeds or if you require very fine-grained temporal analysis beyond what a summarized time-series representation can offer.
Stars
498
Forks
40
Language
Python
License
MIT
Category
Last pushed
Mar 02, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/ucam-eo/tessera"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
mapbox/robosat
Semantic segmentation on aerial and satellite imagery. Extracts features such as: buildings,...
arplaboratory/satellite-thermal-geo-localization
[IROS 2023] Official repository for "Long-range UAV Thermal Geo-localization with Satellite Imagery"
HakaiInstitute/habitat-mapper
Segmentation Tools for Remotely Sensed RPAS Imagery
arplaboratory/UASTHN
[ICRA 2025] Official repository for "UASTHN: Uncertainty-Aware Deep Homography Estimation for...
mehran-tarif/AgriSegment
AgriSegment — A multi-modal plant segmentation suite for agricultural research. It offers four...