Deep Decomposition Learning for Inverse Imaging Problems

Dongdong Chen, Mike E. Davies

Research output: Chapter in Book/Report/Conference proceedingConference contribution

18 Citations (Scopus)


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 empirically show that the proposed framework demonstrates superior performance over recent deep residual learning, unrolled learning and nullspace learning on tasks including compressive sensing medical imaging and natural image super-resolution. Our code is available at
Original languageEnglish
Title of host publicationComputer Vision – ECCV 2020
Subtitle of host publication16th European Conference, Glasgow, UK, August 23–28, 2020
EditorsAndrea Vedaldi, Horst Bischof, Thomas Brox, Jan-Michael Frahm
ISBN (Electronic)978-3-030-58604-1
Publication statusPublished - 3 Nov 2020
Event16th European Conference on Computer Vision 2020 - Glasgow, United Kingdom
Duration: 23 Aug 202028 Aug 2020

Publication series

NameLecture Notes in Computer Science


Conference16th European Conference on Computer Vision 2020
Abbreviated titleECCV 2020
Country/TerritoryUnited Kingdom


Dive into the research topics of 'Deep Decomposition Learning for Inverse Imaging Problems'. Together they form a unique fingerprint.

Cite this