The ionosphere serves as a critical medium for radio signal propagation in outer space. A good morphology of the global TEC distribution is very useful for both ionospheric studies and their relative applications. In this work, a deep learning framework was constructed for better spatial estimation in ionospheric TEC. Both the DCGAN and WGAN-GP were considered, and their performances were evaluated with spatial completion for a regional TEC. The performances were evaluated using the correlation coefficient, RMSE, and MAE. Moreover, the IAAC rapid products were used to make comparisons. The results show that both the DCGAN and WGAN-GP outperformed the IAAC CORG rapid products. The spatial TEC estimation clearly goes well with the solar activity trend. The RMSE differences had a maximum of 0.5035 TECu between the results of 2009 and 2014 for the DCGAN and a maximum of 0.9096 TECu between the results of 2009 and 2014 for the WGAN-GP. Similarly, the MAE differences had a maximum of 0.2606 TECu between the results of 2009 and 2014 for DCGAN and a maximum of 0.3683 TECu between the results of 2009 and 2014 for WGAN-GP. The performances of the CORG, DCGAN, and WGAN-GP were also verified for two selected strong geomagnetic storms in 2014 and 2017. The maximum RMSEs were 1.8354 TECu and 2.2437 TECu for the DCGAN and WGAN-GP in the geomagnetic storm on February 18, 2014, respectively, and the maximum RMSEs were 1.3282 TECu and 1.4814 TECu in the geomagnetic storm on 7 September 2017. The GAN-based framework can extract the detailed features of spatial TEC daily morphologies and the responses during geomagnetic storms.