Solving Inverse Problems in Imaging via Deep Dictionary Learning
In dictionary learning-based inversion, the dictionary and coefficients are learnt adaptively from the image during the inversion process; this is a shallow approach since one layer of the dictionary is learnt. This is the first work which proposes to adaptively learn multiple layers of dictionaries...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8554065/ |
| Summary: | In dictionary learning-based inversion, the dictionary and coefficients are learnt adaptively from the image during the inversion process; this is a shallow approach since one layer of the dictionary is learnt. This is the first work which proposes to adaptively learn multiple layers of dictionaries during inversion. This results in our deep dictionary learning-based inversion formulation. Experiments have been carried out on denoising, super-resolution, and reconstruction. For each problem, our proposed method outperforms the state-of-the-art. |
|---|---|
| ISSN: | 2169-3536 |