Unrolled Variational Bayesian Algorithm for Image Blind Deconvolution
In this paper, we introduce a variational Bayesian algorithm (VBA) for image blind deconvolution. Our VBA generic framework incorporates smoothness priors on the unknown blur/image and possible affine constraints (e.g., sum to one) on the blur kernel, integrating the VBA within a neural network paradigm following an unrolling methodology. The proposed architecture is trained in a supervised fashion, which allows us to optimally set two key hyperparameters of the VBA model and leads to further improvements in terms of resulting visual quality. Various experiments involving grayscale/color images and diverse kernel shapes, are performed. The numerical examples illustrate the high performance of our approach when compared to state-of-the-art techniques based on optimization, Bayesian estimation, or deep learning.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2022 |
---|---|
Erschienen: |
2022 |
Enthalten in: |
Zur Gesamtaufnahme - volume:PP |
---|---|
Enthalten in: |
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society - PP(2022) vom: 20. Dez. |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Huang, Yunshi [VerfasserIn] |
---|
Links: |
---|
Themen: |
---|
Anmerkungen: |
Date Revised 04.04.2023 published: Print-Electronic Citation Status Publisher |
---|
doi: |
10.1109/TIP.2022.3224322 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM35520181X |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM35520181X | ||
003 | DE-627 | ||
005 | 20231226063839.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231226s2022 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1109/TIP.2022.3224322 |2 doi | |
028 | 5 | 2 | |a pubmed24n1183.xml |
035 | |a (DE-627)NLM35520181X | ||
035 | |a (NLM)37015435 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Huang, Yunshi |e verfasserin |4 aut | |
245 | 1 | 0 | |a Unrolled Variational Bayesian Algorithm for Image Blind Deconvolution |
264 | 1 | |c 2022 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Revised 04.04.2023 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status Publisher | ||
520 | |a In this paper, we introduce a variational Bayesian algorithm (VBA) for image blind deconvolution. Our VBA generic framework incorporates smoothness priors on the unknown blur/image and possible affine constraints (e.g., sum to one) on the blur kernel, integrating the VBA within a neural network paradigm following an unrolling methodology. The proposed architecture is trained in a supervised fashion, which allows us to optimally set two key hyperparameters of the VBA model and leads to further improvements in terms of resulting visual quality. Various experiments involving grayscale/color images and diverse kernel shapes, are performed. The numerical examples illustrate the high performance of our approach when compared to state-of-the-art techniques based on optimization, Bayesian estimation, or deep learning | ||
650 | 4 | |a Journal Article | |
700 | 1 | |a Chouzenoux, Emilie |e verfasserin |4 aut | |
700 | 1 | |a Pesquet, Jean-Christophe |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society |d 1992 |g PP(2022) vom: 20. Dez. |w (DE-627)NLM09821456X |x 1941-0042 |7 nnns |
773 | 1 | 8 | |g volume:PP |g year:2022 |g day:20 |g month:12 |
856 | 4 | 0 | |u http://dx.doi.org/10.1109/TIP.2022.3224322 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d PP |j 2022 |b 20 |c 12 |