# EGTM: Event-guided Efficient Turbulence Mitigation

arXiv: https://arxiv.org/abs/2509.03808 · HTML: https://mlsanity.com/paper/2509.03808/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 34 references that are in the map.
- First posted on arXiv 4 Sep 2025.

## Builds on (most cited first, 15 of 15)

- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [Single Frame Atmospheric Turbulence Mitigation: A Benchmark Study and A New Physics-Inspired Transformer Model](https://mlsanity.com/paper/2207.10040/) (2022)
- [Imaging through the Atmosphere using Turbulence Mitigation Transformer](https://mlsanity.com/paper/2207.06465/) (2022)
- [Image Reconstruction of Static and Dynamic Scenes through Anisoplanatic Turbulence](https://mlsanity.com/paper/2009.00071/) (2020)
- [Deep Recurrent Neural Network with Multi-scale Bi-directional Propagation for Video Deblurring](https://mlsanity.com/paper/2112.05150/) (2021)
- [Physics-Driven Turbulence Image Restoration with Stochastic Refinement](https://mlsanity.com/paper/2307.10603/) (2023)
- [Spatio-Temporal Turbulence Mitigation: A Translational Perspective](https://mlsanity.com/paper/2401.04244/) (2024)
- [LTT-GAN: Looking Through Turbulence by Inverting GANs](https://mlsanity.com/paper/2112.02379/) (2021)
- [FluidNexus: 3D Fluid Reconstruction and Prediction from a Single Video](https://mlsanity.com/paper/2503.04720/) (2025)
- [Bridging the Gap Between Computational Photography and Visual Recognition](https://mlsanity.com/paper/1901.09482/) (2019)
- [LED: A Large-scale Real-world Paired Dataset for Event Camera Denoising](https://mlsanity.com/paper/2405.19718/) (2024)
- [Long-range Turbulence Mitigation: A Large-scale Dataset and A Coarse-to-fine Framework](https://mlsanity.com/paper/2407.08377/) (2024)
- [Turb-Seg-Res: A Segment-then-Restore Pipeline for Dynamic Videos with Atmospheric Turbulence](https://mlsanity.com/paper/2404.13605/) (2024)
- [CrossZoom: Simultaneously Motion Deblurring and Event Super-Resolving](https://mlsanity.com/paper/2309.16949/) (2023)
- [Atmospheric turbulence restoration by diffeomorphic image registration and blind deconvolution](https://mlsanity.com/paper/2411.07578/) (2024)

## Built on by (most cited first, 3 of 3)

- [High-speed Imaging through Turbulence with Event-based Light Fields](https://mlsanity.com/paper/2603.14023/) (2026)
- [High-Quality and Efficient Turbulence Mitigation with Events](https://mlsanity.com/paper/2603.20708/) (2026)
- [D2Turb: Depth-Aware Simulation and Decoupled Learning for Single-Frame Atmospheric Turbulence Mitigation](https://mlsanity.com/paper/2605.27460/) (2026)

## Abstract (arXiv)

Turbulence mitigation (TM) aims to remove the stochastic distortions and blurs introduced by atmospheric turbulence into frame cameras. Existing state-of-the-art deep-learning TM methods extract turbulence cues from multiple degraded frames to find the so-called "lucky'', not distorted patch, for "lucky fusion''. However, it requires high-capacity network to learn from coarse-grained turbulence dynamics between synchronous frames with limited frame-rate, thus fall short in computational and storage efficiency. Event cameras, with microsecond-level temporal resolution, have the potential to fundamentally address this bottleneck with efficient sparse and asynchronous imaging mechanism. In light of this, we (i) present the fundamental ``event-lucky insight'' to reveal the correlation between turbulence distortions and inverse spatiotemporal distribution of event streams. Then, build upon this insight, we (ii) propose a novel EGTM framework that extracts pixel-level reliable turbulence-free guidance from the explicit but noisy turbulent events for temporal lucky fusion. Moreover, we (iii) build the first turbulence data acquisition system to contribute the first real-world event-driven TM dataset. Extensive experimental results demonstrate that our approach significantly surpass the existing SOTA TM method by 710 times, 214 times and 224 times in model size, inference latency and model complexity respectively, while achieving the state-of-the-art in restoration quality (+0.94 PSNR and +0.08 SSIM) on our real-world EGTM dataset. This demonstrating the great efficiency merit of introducing event modality into TM task. Demo code and data have been uploaded in supplementary material and will be released once accepted.