An end-to-end deep learning image compression method for satellite images based on entropy model

Yanlong Gao, Haiming Xu, Wei Huang, Hao Bai, Boer Peng, Heyang Xu · 2026

Read An end-to-end deep learning image compression method for satellite images based on entropy model by Yanlong Gao, Haiming Xu, Wei Huang, Hao Bai, Boer Peng, Heyang Xu (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0355234.txt.

Description

Yanlong Gao and five colleagues published this 2026 paper on shrinking satellite images with deep learning. Satellites send down far more picture data than ground links handle easily, and older compression can blur fine detail. Their system, trained end to end, squeezes visible and infrared imagery from a weather satellite instrument.

The method cut files to a small fraction of their starting size, roughly a thirtieth on average, while keeping rebuilt images usable. Large scenes are split into small square blocks, compressed separately, then stitched back together. Faster downlinks mean fresher maps for weather tracking, land surveys, and disaster response.

Catalog record

CREATORYanlong Gao, Haiming Xu, Wei Huang, Hao Bai, Boer Peng, Heyang Xu
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE51432
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0355234

Browse the full library · About the Tower of Babel