End-to-end reconstruction meets data-driven regularization for inverse problems.
Subhadip MukherjeeMarcello CarioniOzan ÖktemCarola-Bibiane SchönliebPublished in: NeurIPS (2021)
Keyphrases
- end to end
- inverse problems
- data driven
- image reconstruction
- emission tomography
- regularization methods
- global optimization
- regularization method
- convex optimization
- optimization methods
- super resolution
- partial differential equations
- congestion control
- optimization problems
- neural network
- early vision
- smoothness constraint
- text localization and recognition
- image enhancement
- medical images
- evolutionary algorithm
- computational complexity