Abstract
The vast majority of image recovery tasks are ill-posed problems. As such, methods that are based on optimization use cost functions that consist of both fidelity and prior (regularization) terms. A recent line of works imposes the prior by the Regularization by Denoising (RED) approach, which exploits the good performance of existing image denoising engines. Yet, the relation of RED to explicit prior terms is still not well understood, as previous work requires too strong assumptions on the denoisers. In this paper, we make two contributions. First, we show that the RED gradient can be seen as a (sub)gradient of a prior function—but taken at a denoised version of the point. As RED is typically applied with a relatively small noise level, this interpretation indicates a similarity between RED and traditional gradients. This leads to our second contribution: We propose to combine RED with the Back-Projection (BP) fidelity term rather than the common Least Squares (LS) term that is used in previous works. We show that the advantages of BP over LS for image deblurring and super-resolution, which have been demonstrated for traditional gradients, carry on to the RED approach.
Original language | English |
---|---|
Title of host publication | 2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings |
Publisher | IEEE Computer Society |
Pages | 1649-1653 |
Number of pages | 5 |
ISBN (Electronic) | 9781665441155 |
DOIs | |
State | Published - 2021 |
Externally published | Yes |
Event | 2021 IEEE International Conference on Image Processing, ICIP 2021 - Anchorage, United States Duration: 19 Sep 2021 → 22 Sep 2021 |
Publication series
Name | Proceedings - International Conference on Image Processing, ICIP |
---|---|
Volume | 2021-September |
ISSN (Print) | 1522-4880 |
Conference
Conference | 2021 IEEE International Conference on Image Processing, ICIP 2021 |
---|---|
Country/Territory | United States |
City | Anchorage |
Period | 19/09/21 → 22/09/21 |
Bibliographical note
Publisher Copyright:© 2021 IEEE
Funding
We considered the RED approach, which exploits existing image denoising engines for solving tasks other than denois-ing. We showed that the RED gradient can be seen as a (sub)gradient of a prior function that is computed at a (typically slightly) denoised version of the point. This similarity between RED and traditional gradients motivated us to combine RED with the BP fidelity term, which has demonstrated improved results for traditional gradients schemes. Various experiments demonstrated the advantages of our BP-RED method over the combination of RED with least squares, used in previous works. Acknowledgment. This research was supported by ERC-StG grant no. 757497 (SPADE).
Funders | Funder number |
---|---|
ERC-STG | |
Horizon 2020 Framework Programme | 757497 |
Keywords
- Back-Projection
- Image deblurring
- Inverse problems
- Regularization by Denoising
- Super-resolution