Solving inverse problems with deep neural networks driven by sparse signal decomposition in a physics-based dictionary.
Gaëtan RensonnetLouise AdamBenoît MacqPublished in: CoRR (2021)
Keyphrases
- inverse problems
- neural network
- sparse representation
- image reconstruction
- compressive sensing
- global optimization
- convex optimization
- wavelet packet
- pattern recognition
- signal processing
- optimization problems
- optimization methods
- early vision
- sparse signal representation
- smoothness constraint
- multi objective
- pairwise
- image processing
- genetic algorithm