The method used to estimate the unfiltered shortwave broadband radiance from the filtered radiances measured by the Geostationary Earth Radiation Budget (GERB) instrument is presented. This unfiltering method is used to generate the first released edition of the GERB-2 dataset. The method involves a set of regressions between the unfiltering factor (i.e.; the ratio of the unfiltered and filtered broadband radiances) and the narrowband observations of the Spinning Enhanced Visible and Infrared Imager (SEVIRI) instrument. The regressions are theoretically derived from a large database of simulated spectral radiance curves obtained by radiative transfer computations. The generation of the database is fully described. Different sources of error that may affect the GERB unfiltering have been identified and the associated error magnitudes are assessed on this database. For most of the earth–atmosphere conditions, the error introduced during the unfiltering process is below 1%. In some conditions (e.g.; low sun elevation above the horizon) the error can present a higher relative value, but the absolute error value remains well under the accuracy goal of 1% of the full instrument scale (2.4 W m−2 sr−1). To increase the confidence level, the edition 1 unfiltered radiances of GERB-2 are validated by cross comparison with collocated and coangular Clouds and the Earth’s Radiant Energy System (CERES) observations for different scene types. In addition to an overall offset between the two instruments, the intercomparisons indicate a scene-type dependency up to 4% in unfiltered radiance. Further studies are required to confirm the cause, but an insufficiently accurate characterization of the shortwave spectral response of the GERB instrument in the visible part of the spectrum is one area under further investigation.