Event-Based Desnowing for Autonomous Driving
IEEE Transactions on Robotics · 2026 · 42 · 2898-2911
DOI: 10.1109/tro.2026.3697155 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Robotics, 2026. Verfasst von Manasi Muglikar und 3 weiteren Autor:innen. Die Arbeit nennt 49 Literaturangaben. Gefördert von: European Research Council.
Abstract (Originalsprache)
Adverse weather conditions, particularly heavy snowfall, pose significant challenges to both human drivers and autonomous vehicles. Traditional image-based desnowing methods often introduce hallucination artifacts as they rely solely on spatial information, while video-based approaches require high frame rates and suffer from alignment artifacts at lower frame rates. Camera parameters, such as exposure time, also influence the appearance of snowflakes, making the problem difficult to solve and heavily dependent on network generalization. In this article, we propose to address the challenge of desnowing by using event cameras, which offer compressed visual information with submillisecond latency, making them ideal for desnowing images, even in the presence of ego-motion. Our method leverages the fact that snowflake occlusions appear with a very distinctive streak signature in the spatiotemporal representation of event data. We design an attention-based module that focuses on events along these streaks to determine when a background point was occluded and use this information to recover its original intensity. We benchmark our method on DSEC-Snow, a new dataset created using a green-screen technique that overlays prerecorded snowfall data onto the existing DSEC driving dataset, resulting in precise ground truth and synchronized image and event streams. Our approach outperforms state-of-the-art desnowing methods by 3 dB in peak signal-to-noise ratio for image reconstruction. Moreover, we show that off-the-shelf computer vision algorithms can be applied to our reconstructions for tasks, such as depth estimation and optical flow, achieving a 20% performance improvement over other desnowing methods. Our work represents a crucial step toward enhancing the reliability and safety of vision systems in challenging winter conditions, paving the way for more robust, all-weather-capable applications. Code, dataset, and video are available online at https://rpg.ifi.uzh.ch/evsnow.html.
Förderung
- European Research Council
Zitieren
APA
Muglikar, M., Messikommer, N., Cannici, M., & Scaramuzza, D. (2026). Event-Based Desnowing for Autonomous Driving. IEEE Transactions on Robotics, 42, 2898-2911. https://doi.org/10.1109/tro.2026.3697155
Vancouver
Muglikar M, Messikommer N, Cannici M, Scaramuzza D. Event-Based Desnowing for Autonomous Driving. IEEE Transactions on Robotics. 2026;42:2898-2911. doi:10.1109/tro.2026.3697155
BibTeX
@article{Muglikar2026,
author = {Muglikar, Manasi and Messikommer, Nico and Cannici, Marco and Scaramuzza, Davide},
title = {Event-Based Desnowing for Autonomous Driving},
journal = {IEEE Transactions on Robotics},
year = {2026},
volume = {42},
pages = {2898--2911},
doi = {10.1109/tro.2026.3697155}
}
EUVIMED