R2D2 RI

Residual-to-Residual DNN series for high-Dynamic range imaging

Main codes & Tutorials

Papers & Paper codes

Towards a robust R2D2 paradigm for radio-interferometric imaging: revisiting DNN training and architecture
A. Aghabiglou, C. S. Chu, C. Tang, A. Dabbech, Y. Wiaux, Submitted for publication at ApJS, 2025.
ArXiv:2503.02554v1

R2D2 image reconstruction with model uncertainty quantification in radio astronomy
A. Aghabiglou, C. S. Chu, A. Dabbech, Y. Wiaux, IEEE EUSIPCO 2024, 1926--1931, 2024.
ArXiv:2403.18052 | DOI:10.23919/EUSIPCO63174.2024.10715010

The R2D2 deep neural network series paradigm for fast precision imaging in radio astronomy
A. Aghabiglou, C. S. Chu, A. Dabbech, Y. Wiaux, ApJS, 273(1):3, 2024.
ArXiv:2403.05452 | DOI:10.3847/1538-4365/ad46f5

CLEANing Cygnus A deep and fast with R2D2
A. Dabbech, A. Aghabiglou, C. S. Chu, Y. Wiaux, ApJL, 966(2):L34, 2024.
ArXiv:2309.03291 | DOI:10.3847/2041-8213/ad41df

Deep network series for large-scale high-dynamic range imaging
A. Aghabiglou, M. Terris, A. Jackson, Y. Wiaux, in Proc. IEEE ICASSP 2023, pp. 1–5, 2023.
ArXiv:2210.16060| DOI:10.1109/ICASSP49357.2023.10094843