Deep Decomposition Learning for Inverse Imaging Problems

11/25/2019
by   Dongdong Chen, et al.
0

Deep learning is emerging as a new paradigm for solving inverse imaging problems. However, the deep learning methods often lack the assurance of traditional physics-based methods due to the lack of physical information considerations in neural network training and deploying. The appropriate supervision and explicit calibration by the information of the physic model can enhance the neural network learning and its practical performance. In this paper, inspired by the geometry that data can be decomposed by two components from the null-space of the forward operator and the range space of its pseudo-inverse, we train neural networks to learn the two components and therefore learn the decomposition, i.e. we explicitly reformulate the neural network layers as learning range-nullspace decomposition functions with reference to the layer inputs, instead of learning unreferenced functions. We show that the decomposition networks not only produce superior results, but also enjoy good interpretability and generalization. We demonstrate the advantages of decomposition learning on different inverse problems including compressive sensing and image super-resolution as examples.

READ FULL TEXT

page 7

page 8

research
06/18/2020

Model-Aware Regularization For Learning Approaches To Inverse Problems

There are various inverse problems – including reconstruction problems a...
research
06/09/2021

Ghosts in Neural Networks: Existence, Structure and Role of Infinite-Dimensional Null Space

Overparametrization has been remarkably successful for deep learning stu...
research
05/02/2023

Deep Learning-Assisted Simultaneous Targets Sensing and Super-Resolution Imaging

Recently, metasurfaces have experienced revolutionary growth in the sens...
research
07/08/2022

A new perspective on the fictitious space lemma

In the present contribution we propose a new proof of the so-called fict...
research
01/19/2021

Deep Feedback Inverse Problem Solver

We present an efficient, effective, and generic approach towards solving...
research
09/12/2019

CvxNets: Learnable Convex Decomposition

Any solid object can be decomposed into a collection of convex polytopes...
research
12/21/2021

Regularization from examples via neural networks for parametric inverse problems: topology matters

In this work we deal with parametric inverse problems, which consist in ...

Please sign up or login with your details

Forgot password? Click here to reset