NER-Net+ : Seeing Motion at Nighttime With an Event Camera

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 (mic...

Description complète

Détails bibliographiques
Publié dans:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 47(2025), 6 vom: 03. Mai, Seite 4768-4786
Auteur principal: Liu, Haoyue (Auteur)
Autres auteurs: Xu, Jinghan, Peng, Shihan, Chang, Yi, Zhou, Hanyu, Duan, Yuxing, Zhu, Lin, Tian, Yonghong, Yan, Luxin
Format: Article en ligne
Langue:English
Publié: 2025
Accès à la collection:IEEE transactions on pattern analysis and machine intelligence
Sujets:Journal Article
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