GSNR: Graph Smooth Null-Space Representation for Inverse Problems
Learned graph-smooth null-space components for regularization into Plug-and-Play, Unrolling, Deep Image Prior, and Diffusion Models to boost reconstructions across deblurring, compressed sensing, demosaicing, and super-resolution.
Feb 23, 2026
NPN: Non-Linear Projections of the Null-Space for Imaging Inverse Problems
Null-space–aware prior that plugs into PnP, unrolling, DIP, and diffusion solvers to boost reconstructions across CS, MRI, CT, and deblurring.
Dec 1, 2025
Learning to Reconstruct Signals With Inexact Sensing Operator via Knowledge Distillation
2025 International Conference on Acoustics, Speech, and Signal Processing
Jan 27, 2025
Improving Compressive Imaging Recovery via Measurement Augmentation
2025 International Conference on Acoustics, Speech, and Signal Processing
Jan 27, 2025
Compressive Imaging Reconstruction via Conditional Diffusion Model With Augmented Measurements
2025 International Conference on Acoustics, Speech, and Signal Processing
Jan 27, 2025
Deep Learned Non-Linear Propagation Model Regularizer for Compressive Spectral Imaging
IEEE Transactions on Computational Imaging
Jul 5, 2024
Learning Point Spread Function Invertibility Assessment for Image Deconvolution
EUSIPCO 2024
May 25, 2024
Learning a Spatially-Variant Propagation Model for Compressive Spectral Imaging
Computational Optical Sensing and Imaging 2023
Aug 14, 2023
Compressive Spectral Image Reconstruction by using a Deep Image Prior with a Mismatch Regularizer
Computational Optical Sensing and Imaging 2022
Jul 11, 2022