.png){kind=icon}
返回
Event-Based Dynamic Turbulence Mitigation
.png){kind=icon}
PRE
AI
DOI：10.1109/LSP.2025.3648967.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Atmospheric turbulence induces coupled spatio-temporal distortions, including blur, geometric deformation, and temporal jitter, which severely degrade image quality.We propose EvTurM, a practical framework leveraging event camera data for dynamic turbulence mitigation with precise motion cues and stable temporal modeling. Leveraging the high temporal resolution and dynamic range of events, EvTurM achieves robust restoration under diverse turbulence conditions. EvTurM comprises two key modules: (1) the event-aware modality enhancement module, which uses event-derived motion to enrich RGB features and recover structural details, and (2) the bidirectional modality calibration module, which jointly aligns RGB and event features in forward and backward propagation to reduce misalignment and enhance temporal consistency. Extensive experiments show EvTurM consistently surpasses existing methods and achieves superior performance.
Keyword:
Atmospheric turbulence
event camera
video restoration
multi-modal fusion
期刊
I
IF:
3.9
论文数:
622
被引数:
0
机构
引用论文
分享收藏
分享收藏Boosting Spike Camera Image Reconstruction from a Perspective of Dealing with Spike Fluctuations.png)
IF0
PREAI
分享收藏
查看更多内容