|
|
|
|
| LEADER |
01000caa a22002652 4500 |
| 001 |
NLM379240114 |
| 003 |
DE-627 |
| 005 |
20241029232533.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
241024s2024 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TIP.2024.3480696
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1584.xml
|
| 035 |
|
|
|a (DE-627)NLM379240114
|
| 035 |
|
|
|a (NLM)39437280
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Deng, Haoyou
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Toward Blind Flare Removal Using Knowledge-Driven Flare-Level Estimator
|
| 264 |
|
1 |
|c 2024
|
| 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 28.10.2024
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Lens flare is a common phenomenon when strong light rays arrive at the camera sensor and a clean scene is consequently mixed up with various opaque and semi-transparent artifacts. Existing deep learning methods are always constrained with limited real image pairs for training. Though recent synthesis-based approaches are found effective, synthesized pairs still deviate from the real ones as the mixing mechanism of flare artifacts and scenes in the wild always depends on a line of undetermined factors, such as lens structure, scratches, etc. In this paper, we present a new perspective from the blind nature of the flare removal task in a knowledge-driven manner. Specifically, we present a simple yet effective flare-level estimator to predict the corruption level of a flare-corrupted image. The estimated flare-level can be interpreted as additive information of the gap between corrupted images and their flare-free correspondences to facilitate a network at both training and testing stages adaptively. Besides, we utilize a flare-level modulator to better integrate the estimations into networks. We also devise a flare-aware block for more accurate flare recognition and reconstruction. Additionally, we collect a new real-world flare dataset for benchmarking, namely WiderFlare. Extensive experiments on three benchmark datasets demonstrate that our method outperforms state-of-the-art methods quantitatively and qualitatively
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Li, Lida
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhang, Feng
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Li, Zhiqiang
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Xu, Bin
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Lu, Qingbo
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Gao, Changxin
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Sang, Nong
|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 33(2024) vom: 22., Seite 6114-6128
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnns
|
| 773 |
1 |
8 |
|g volume:33
|g year:2024
|g day:22
|g pages:6114-6128
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2024.3480696
|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 33
|j 2024
|b 22
|h 6114-6128
|