UPADNet applies phase-amplitude decomposition with novel LMMSE estimators inside an unrolled iterative algorithm, outperforming prior deblurring networks on GoPro, RealBlur, and COCO.
Linear Algebra and its Applications , volume=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
NL-RMM-GKS extends majorization-minimization and Krylov subspace recycling to nonlinear inverse problems with uncertain forward operators, offering alternating minimization, variable projection, and streaming variants for dynamic imaging.
citing papers explorer
-
Leveraging Phase Information to Boost Unrolled Network Learning for Image Deblurring
UPADNet applies phase-amplitude decomposition with novel LMMSE estimators inside an unrolled iterative algorithm, outperforming prior deblurring networks on GoPro, RealBlur, and COCO.
-
Nonlinear RMM-GKS for Large-Scale Dynamic and Streaming Inverse Problems with Uncertain Forward Operators
NL-RMM-GKS extends majorization-minimization and Krylov subspace recycling to nonlinear inverse problems with uncertain forward operators, offering alternating minimization, variable projection, and streaming variants for dynamic imaging.