Abstract
Deep learning (DL) has shown remarkable results in solving inverse problems in various domains. In particular, the Tikhonet approach is very powerful in deconvolving optical astronomical images. However, this approach only uses the ℓ2 loss, which does not guarantee the preservation of physical information (e.g., flux and shape) of the object that is reconstructed in the image. A new loss function has been proposed in the framework of sparse deconvolution that better preserves the shape of galaxies and reduces the pixel error. In this paper, we extend the Tikhonet approach to take this shape constraint into account and apply our new DL method, called ShapeNet, to a simulated optical and radio-interferometry dataset. The originality of the paper relies on i) the shape constraint we use in the neural network framework, ii) the application of DL to radio-interferometry image deconvolution for the first time, and iii) the generation of a simulated radio dataset that we make available for the community. A range of examples illustrates the results.
Subject
Space and Planetary Science,Astronomy and Astrophysics
Reference21 articles.
1. Bertero M., & Boccacci P. 1998, Introduction to Inverse Problems in Imaging (CRC Press)
2. Bonaldi A., Bonato M., Galluzzi V., et al. 2019, Astrophysics Source Code Library [1906.008]
3. Chollet F. 2015, Keras, https://github.com/keras-team/keras/
4. Dong J., Roth S., & Schiele B. 2021, ArXiv e-prints [arXiv:2103.09962]
5. LOFAR sparse image reconstruction
Cited by
5 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献