synapse-sr 0.4.0

Sentinel-2 at 2 m, with every pixel accounted for

synapse-sr turns a Sentinel-2 L2A scene into a 2.0 m red / green / blue / near-infrared GeoTIFF. A physical model of the instrument pins everything the satellite measured. The network only adds what 10 m pixels cannot show, and every output says which pixels came from the measurement and which came from the learned prior.

pip install synapse-sr

import synapse_sr
result = synapse_sr.super_resolve("scene.tif")

import synapse_sr

r = synapse_sr.super_resolve("sentinel2_l2a.tif")   # progress bar, then a 5x larger result
r.save("sentinel2_2m.tif")                           # georeferenced, same CRS and bounds
r.summary()                                          # size, consistency, support, time

synapse-sr sentinel2_l2a.tif sentinel2_2m.tif        # the same from the shell
synapse-sr --fetch 12.92,77.50 --dates 2025-01-01:2025-03-15 out.tif --preview preview.png   # download + run
synapse-sr scenes/ scenes_2m/ --cog                  # a whole folder, as Cloud-Optimised GeoTIFFs

Every common task on one page: cheat sheet. AI assistants and agents can read the whole documentation from llms.txt.

Benchmarks

Official opensr-test protocol (Aybar et al.): Sentinel-2 L2A input, harmonised high-resolution references, opensr_test.Metrics() defaults, mean over its five datasets (NAIP, SPOT, Spain urban, Spain crops, VENµS; 178 scenes). Every model at its native scale, compared on the reference grid.

Best in bold. SYNAPSE runs with the package defaults (synapse_sr.super_resolve). Flash processes a 1.28 km scene in about 1 s on a laptop CPU; Pro in about 5 s on a GPU.

What it is for

Worked examples for each: Applications.

Flash or Pro

Both run the same observation-consistent pipeline and score within a whisker of each other on the benchmark above. Use Flash for speed and anywhere-deployment, Pro for the most detail on a GPU. synapse-sr --models lists every published checkpoint.

Why trust the output

import synapse_sr
r = synapse_sr.super_resolve("scene.tif")

r.x_base        # what the 10 m observation determines
r.prior         # what the network added (x_base + prior == image), invisible to the sensor
r.support       # per pixel: 2 observation-determined, 1 medium, 0 prior-dominated or invalid
r.uncertainty() # calibrated expected error per pixel and band
r.consistency   # how closely re-observing the output reproduces the input, in sensor-noise units

x_hat = x_base + P_N(delta): P_N removes every component the sensor could have seen from the network's output, so the network cannot contradict the measurement. See How it works.

Runs everywhere

synapse-sr --env shows what is active on your machine.

Documentation

Quick start · Colab and Kaggle · Applications · Examples · API

@software{synapse_sr,
  title  = {synapse-sr: observation-consistent super-resolution of Sentinel-2 imagery},
  author = {Naidu, Sharadh},
  year   = {2026},
  url    = {https://github.com/SharadhNaidu/synapse-sr}
}