Bibliographic Details
| Title: |
Compressed Sensing of Generative Sparse-latent (GSL) Signals |
| Authors: |
Honoré, Antoine, Ghosh, Anubhab, Chatterjee, Saikat |
| Publication Year: |
2023 |
| Collection: |
Computer Science |
| Subject Terms: |
Computer Science - Machine Learning, Computer Science - Artificial Intelligence |
| More Details: |
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.
Comment: Accepted at 31st European Signal Processing Conference, EUSIPCO 2023 |
| Document Type: |
Working Paper |
| Access URL: |
http://arxiv.org/abs/2310.15119 |
| Accession Number: |
edsarx.2310.15119 |
| Database: |
arXiv |
