Paper ID: 2310.15119
Compressed Sensing of Generative Sparse-latent (GSL) Signals
Antoine Honoré, Anubhab Ghosh, Saikat Chatterjee
We consider reconstruction of an ambient signal in a compressed sensing (CS) setup where the ambient signal has a neural network based generative model. The generative model has a sparse-latent input and we refer to the generated ambient signal as generative sparse-latent signal (GSL). The proposed sparsity inducing reconstruction algorithm is inherently non-convex, and we show that a gradient based search provides a good reconstruction performance. We evaluate our proposed algorithm using simulated data.
Submitted: Oct 16, 2023