High-speed Imaging through Turbulence with Event-based Light Fields

Yu-Hsiang Huang Levi Burner Sachin Shah Ziyuan Qu Adithya Pediredla Christopher A. Metzler
European Conference on Computer Vision (ECCV) — 2026

EventLightFieldTurbulence teaser

This work introduces and demonstrates the first system capable of imaging fast-moving extended non-rigid objects through strong atmospheric turbulence at high frame rate. Event cameras are a novel sensing architecture capable of estimating high-speed imagery at thousands of frames per second; however, on their own event cameras are unable to disambiguate scene motion from turbulence. We overcome this limitation using event-based light field cameras: by simultaneously capturing multiple views of a scene, event-based light field cameras and machine learning-based reconstruction algorithms can disambiguate motion-induced dynamics, which produce events strongly correlated across views, from turbulence-induced dynamics, which produce events weakly correlated across views. Tabletop experiments demonstrate that event-based light fields can overcome strong turbulence while imaging high-speed objects traveling at up to 16,000 pixels per second.


@article{huang2026high,
  title={High-speed Imaging through Turbulence with Event-based Light Fields},
  author={Huang, Yu-Hsiang and Burner, Levi and Shah, Sachin and Qu, Ziyuan and Pediredla, Adithya and Metzler, Christopher A},
  journal={arXiv preprint arXiv:2603.14023},
  year={2026}
}