|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM358089018 |
| 003 |
DE-627 |
| 005 |
20231226074011.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231226s2023 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TIP.2023.3283922
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1193.xml
|
| 035 |
|
|
|a (DE-627)NLM358089018
|
| 035 |
|
|
|a (NLM)37307185
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Xia, Bin
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Meta-Learning-Based Degradation Representation for Blind Super-Resolution
|
| 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 20.06.2023
|
| 500 |
|
|
|a Date Revised 20.06.2023
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Blind image super-resolution (blind SR) aims to generate high-resolution (HR) images from low-resolution (LR) input images with unknown degradations. To enhance the performance of SR, the majority of blind SR methods introduce an explicit degradation estimator, which helps the SR model adjust to unknown degradation scenarios. Unfortunately, it is impractical to provide concrete labels for the multiple combinations of degradations (e. g., blurring, noise, or JPEG compression) to guide the training of the degradation estimator. Moreover, the special designs for certain degradations hinder the models from being generalized for dealing with other degradations. Thus, it is imperative to devise an implicit degradation estimator that can extract discriminative degradation representations for all types of degradations without requiring the supervision of degradation ground-truth. To this end, we propose a Meta-Learning based Region Degradation Aware SR Network (MRDA), including Meta-Learning Network (MLN), Degradation Extraction Network (DEN), and Region Degradation Aware SR Network (RDAN). To handle the lack of ground-truth degradation, we use the MLN to rapidly adapt to the specific complex degradation after several iterations and extract implicit degradation information. Subsequently, a teacher network MRDAT is designed to further utilize the degradation information extracted by MLN for SR. However, MLN requires iterating on paired LR and HR images, which is unavailable in the inference phase. Therefore, we adopt knowledge distillation (KD) to make the student network learn to directly extract the same implicit degradation representation (IDR) as the teacher from LR images. Furthermore, we introduce an RDAN module that is capable of discerning regional degradations, allowing IDR to adaptively influence various texture patterns. Extensive experiments under classic and real-world degradation settings show that MRDA achieves SOTA performance and can generalize to various degradation processes
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Tian, Yapeng
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhang, Yulun
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Hang, Yucheng
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Yang, Wenming
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Liao, Qingmin
|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 32(2023) vom: 12., Seite 3383-3396
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnns
|
| 773 |
1 |
8 |
|g volume:32
|g year:2023
|g day:12
|g pages:3383-3396
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2023.3283922
|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 32
|j 2023
|b 12
|h 3383-3396
|