Deep Decomposition Learning for Inverse Imaging Problems

Dongdong Chen, Mike E. Davies

Research output: Contribution to conferencePaperpeer-review

Abstract / Description of output

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.
Original languageUndefined/Unknown
Number of pages17
Publication statusPublished - 16 Jul 2020
Event16th European Conference on Computer Vision - Virtual conference
Duration: 23 Aug 202028 Aug 2020


Conference16th European Conference on Computer Vision
Abbreviated titleECCV 2020
CityVirtual conference
Internet address

Keywords / Materials (for Non-textual outputs)

  • eess.IV
  • cs.CV

Cite this