|
|
|
|
| LEADER |
01000caa a22002652c 4500 |
| 001 |
NLM385079869 |
| 003 |
DE-627 |
| 005 |
20250509031033.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
250508s2025 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2025.3545936
|2 doi
|
| 028 |
5 |
2 |
|a pubmed25n1399.xml
|
| 035 |
|
|
|a (DE-627)NLM385079869
|
| 035 |
|
|
|a (NLM)40031659
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Liu, Haoyue
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a NER-Net+
|b Seeing Motion at Nighttime With an Event Camera
|
| 264 |
|
1 |
|c 2025
|
| 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 07.05.2025
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a We focus on a very challenging task: imaging at nighttime dynamic scenes. Conventional RGB cameras struggle with the trade-off between long exposure for low-light imaging and short exposure for capturing dynamic scenes. Event cameras react to dynamic changes, with their high temporal resolution (microsecond) and dynamic range (120 dB), and thus offer a promising alternative. However, existing methods are mostly based on simulated datasets due to the lack of paired event-clean image data for nighttime conditions, where the domain gap leads to performance limitations in real-world scenarios. Moreover, most existing event reconstruction methods are tailored for daytime data, overlooking issues unique to low-light events at night, such as strong noise, temporal trailing, and spatial non-uniformity, resulting in unsatisfactory reconstruction results. To address these challenges, we construct the first real paired low-light event dataset (RLED) through a co-axial imaging system, comprising 80,400 spatially and temporally aligned image GTs and low-light events, which provides a unified training and evaluation dataset for existing methods. We further conduct a comprehensive analysis of the causes and characteristics of strong noise, temporal trailing, and spatial non-uniformity in nighttime events, and propose a nighttime event reconstruction network (NER-Net+). It includes a learnable event timestamps calibration module (LETC) to correct the temporal trailing events and a non-stationary spatio-temporal information enhancement module (NSIE) to suppress sensor noise and spatial non-uniformity. Extensive experiments demonstrate that the proposed method outperforms state-of-the-art methods in visual quality and generalization on real-world nighttime datasets
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Xu, Jinghan
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Peng, Shihan
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Chang, Yi
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhou, Hanyu
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Duan, Yuxing
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhu, Lin
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Tian, Yonghong
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Yan, Luxin
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 47(2025), 6 vom: 03. Mai, Seite 4768-4786
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnas
|
| 773 |
1 |
8 |
|g volume:47
|g year:2025
|g number:6
|g day:03
|g month:05
|g pages:4768-4786
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2025.3545936
|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 47
|j 2025
|e 6
|b 03
|c 05
|h 4768-4786
|