Learning Efficient Meshflow and Optical Flow from Event Cameras

In this paper, we explore the problem of event-based meshflow estimation, a novel task that involves predicting a spatially smooth sparse motion field from event cameras. To start, we review the state-of-the-art in event-based flow estimation, highlighting two key areas for further research: i) the...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - PP(2025) vom: 26. Sept.
1. Verfasser: Luo, Xinglong (VerfasserIn)
Weitere Verfasser: Luo, Ao, Luo, Kunming, Wang, Zhengning, Tan, Ping, Zeng, Bing, Liu, Shuaicheng
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2025
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000naa a22002652c 4500
001 NLM393153479
003 DE-627
005 20250927232314.0
007 cr uuu---uuuuu
008 250927s2025 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2025.3615144  |2 doi 
028 5 2 |a pubmed25n1582.xml 
035 |a (DE-627)NLM393153479 
035 |a (NLM)41004360 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Luo, Xinglong  |e verfasserin  |4 aut 
245 1 0 |a Learning Efficient Meshflow and Optical Flow from Event Cameras 
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 26.09.2025 
500 |a published: Print-Electronic 
500 |a Citation Status Publisher 
520 |a In this paper, we explore the problem of event-based meshflow estimation, a novel task that involves predicting a spatially smooth sparse motion field from event cameras. To start, we review the state-of-the-art in event-based flow estimation, highlighting two key areas for further research: i) the lack of meshflow-specific event datasets and methods, and ii) the underexplored challenge of event data density. First, we generate a large-scale High-Resolution Event Meshflow (HREM) dataset, which showcases its superiority by encompassing the merits of high resolution at 1280×720, handling dynamic objects and complex motion patterns, and offering both optical flow and meshflow labels. These aspects have not been fully explored in previous works. Besides, we propose Efficient Event-based MeshFlow (EEMFlow) network, a lightweight model featuring a specially crafted encoder-decoder architecture to facilitate swift and accurate meshflow estimation. Furthermore, we upgrade EEMFlow network to support dense event optical flow, in which a Confidence-induced Detail Completion (CDC) module is proposed to preserve sharp motion boundaries. We conduct comprehensive experiments to show the exceptional performance and runtime efficiency (30× faster) of our EEMFlow model compared to the recent state-of-the-art flow method. As an extension, we expand HREM into HREM+, a multi-density event dataset contributing to a thorough study of the robustness of existing methods across data with varying densities, and propose an Adaptive Density Module (ADM) to adjust the density of input event data to a more optimal range, enhancing the model's generalization ability. We empirically demonstrate that ADM helps to significantly improve the performance of EEMFlow and EEMFlow+ by 8% and 10%, respectively 
650 4 |a Journal Article 
700 1 |a Luo, Ao  |e verfasserin  |4 aut 
700 1 |a Luo, Kunming  |e verfasserin  |4 aut 
700 1 |a Wang, Zhengning  |e verfasserin  |4 aut 
700 1 |a Tan, Ping  |e verfasserin  |4 aut 
700 1 |a Zeng, Bing  |e verfasserin  |4 aut 
700 1 |a Liu, Shuaicheng  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g PP(2025) vom: 26. Sept.  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnas 
773 1 8 |g volume:PP  |g year:2025  |g day:26  |g month:09 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2025.3615144  |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 PP  |j 2025  |b 26  |c 09