|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM347753132 |
| 003 |
DE-627 |
| 005 |
20231226034603.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231226s2023 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2022.3215571
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1159.xml
|
| 035 |
|
|
|a (DE-627)NLM347753132
|
| 035 |
|
|
|a (NLM)36260582
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Zheng, Dihan
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Learn From Unpaired Data for Image Restoration
|b A Variational Bayes Approach
|
| 264 |
|
1 |
|c 2023
|
| 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 Completed 10.04.2023
|
| 500 |
|
|
|a Date Revised 11.04.2023
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Collecting paired training data is difficult in practice, but the unpaired samples broadly exist. Current approaches aim at generating synthesized training data from unpaired samples by exploring the relationship between the corrupted and clean data. This work proposes LUD-VAE, a deep generative method to learn the joint probability density function from data sampled from marginal distributions. Our approach is based on a carefully designed probabilistic graphical model in which the clean and corrupted data domains are conditionally independent. Using variational inference, we maximize the evidence lower bound (ELBO) to estimate the joint probability density function. Furthermore, we show that the ELBO is computable without paired samples under the inference invariant assumption. This property provides the mathematical rationale of our approach in the unpaired setting. Finally, we apply our method to real-world image denoising, super-resolution, and low-light image enhancement tasks and train the models using the synthetic data generated by the LUD-VAE. Experimental results validate the advantages of our method over other approaches
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Zhang, Xiaowen
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Ma, Kaisheng
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Bao, Chenglong
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 45(2023), 5 vom: 19. Mai, Seite 5889-5903
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:45
|g year:2023
|g number:5
|g day:19
|g month:05
|g pages:5889-5903
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2022.3215571
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 45
|j 2023
|e 5
|b 19
|c 05
|h 5889-5903
|