|
|
|
|
LEADER |
01000naa a22002652 4500 |
001 |
NLM360487416 |
003 |
DE-627 |
005 |
20231226083122.0 |
007 |
cr uuu---uuuuu |
008 |
231226s2023 xx |||||o 00| ||eng c |
024 |
7 |
|
|a 10.1109/TIP.2023.3301332
|2 doi
|
028 |
5 |
2 |
|a pubmed24n1201.xml
|
035 |
|
|
|a (DE-627)NLM360487416
|
035 |
|
|
|a (NLM)37549080
|
040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
041 |
|
|
|a eng
|
100 |
1 |
|
|a Lv, Xiaoqian
|e verfasserin
|4 aut
|
245 |
1 |
0 |
|a Unsupervised Low-Light Video Enhancement With Spatial-Temporal Co-Attention Transformer
|
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 Revised 16.08.2023
|
500 |
|
|
|a published: Print-Electronic
|
500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
520 |
|
|
|a Existing low-light video enhancement methods are dominated by Convolution Neural Networks (CNNs) that are trained in a supervised manner. Due to the difficulty of collecting paired dynamic low/normal-light videos in real-world scenes, they are usually trained on synthetic, static, and uniform motion videos, which undermines their generalization to real-world scenes. Additionally, these methods typically suffer from temporal inconsistency (e.g., flickering artifacts and motion blurs) when handling large-scale motions since the local perception property of CNNs limits them to model long-range dependencies in both spatial and temporal domains. To address these problems, we propose the first unsupervised method for low-light video enhancement to our best knowledge, named LightenFormer, which models long-range intra- and inter-frame dependencies with a spatial-temporal co-attention transformer to enhance brightness while maintaining temporal consistency. Specifically, an effective but lightweight S-curve Estimation Network (SCENet) is first proposed to estimate pixel-wise S-shaped non-linear curves (S-curves) to adaptively adjust the dynamic range of an input video. Next, to model the temporal consistency of the video, we present a Spatial-Temporal Refinement Network (STRNet) to refine the enhanced video. The core module of STRNet is a novel Spatial-Temporal Co-attention Transformer (STCAT), which exploits multi-scale self- and cross-attention interactions to capture long-range correlations in both spatial and temporal domains among frames for implicit motion estimation. To achieve unsupervised training, we further propose two non-reference loss functions based on the invertibility of the S-curve and the noise independence among frames. Extensive experiments on the SDSD and LLIV-Phone datasets demonstrate that our LightenFormer outperforms state-of-the-art methods
|
650 |
|
4 |
|a Journal Article
|
700 |
1 |
|
|a Zhang, Shengping
|e verfasserin
|4 aut
|
700 |
1 |
|
|a Wang, Chenyang
|e verfasserin
|4 aut
|
700 |
1 |
|
|a Zhang, Weigang
|e verfasserin
|4 aut
|
700 |
1 |
|
|a Yao, Hongxun
|e verfasserin
|4 aut
|
700 |
1 |
|
|a Huang, Qingming
|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: 07., Seite 4701-4715
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnns
|
773 |
1 |
8 |
|g volume:32
|g year:2023
|g day:07
|g pages:4701-4715
|
856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2023.3301332
|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 07
|h 4701-4715
|