# EventFly: Event Camera Perception from Ground to the Sky

arXiv: https://arxiv.org/abs/2503.19916 · HTML: https://mlsanity.com/paper/2503.19916/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 78 of its 107 references that are in the map.
- First posted on arXiv 25 Mar 2025.

## Builds on (most cited first, 30 of 78)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/1811.12833/) (2018)
- [Learning to Adapt Structured Output Space for Semantic Segmentation](https://mlsanity.com/paper/1802.10349/) (2018)
- [High Speed and High Dynamic Range Video with an Event Camera](https://mlsanity.com/paper/1906.07165/) (2019)
- [Unsupervised Event-based Learning of Optical Flow, Depth, and Egomotion](https://mlsanity.com/paper/1812.08156/) (2018)
- [DSEC: A Stereo Event Camera Dataset for Driving Scenarios](https://mlsanity.com/paper/2103.06011/) (2021)
- [DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation](https://mlsanity.com/paper/2111.14887/) (2021)
- [Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2101.10979/) (2021)
- [The Multi Vehicle Stereo Event Camera Dataset: An Event Camera Dataset for 3D Perception](https://mlsanity.com/paper/1801.10202/) (2018)
- [CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers](https://mlsanity.com/paper/2203.04838/) (2022)
- [DACS: Domain Adaptation via Cross-domain Mixed Sampling](https://mlsanity.com/paper/2007.08702/) (2020)
- [EV-FlowNet: Self-Supervised Optical Flow Estimation for Event-based Cameras](https://mlsanity.com/paper/1802.06898/) (2018)
- [Event-based Vision meets Deep Learning on Steering Prediction for Self-driving Cars](https://mlsanity.com/paper/1804.01310/) (2018)
- [Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision](https://mlsanity.com/paper/2004.07703/) (2020)
- [Learning to Detect Objects with a 1 Megapixel Event Camera](https://mlsanity.com/paper/2009.13436/) (2020)
- [MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation](https://mlsanity.com/paper/2212.01322/) (2022)
- [Video to Events: Recycling Video Datasets for Event Cameras](https://mlsanity.com/paper/1912.03095/) (2019)
- [HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation](https://mlsanity.com/paper/2204.13132/) (2022)
- [Recurrent Vision Transformers for Object Detection with Event Cameras](https://mlsanity.com/paper/2212.05598/) (2022)
- [A review of domain adaptation without target labels](https://mlsanity.com/paper/1901.05335/) (2019)
- [E-RAFT: Dense Optical Flow from Event Cameras](https://mlsanity.com/paper/2108.10552/) (2021)
- [Ultimate SLAM? Combining Events, Images, and IMU for Robust Visual SLAM in HDR and High Speed Scenarios](https://mlsanity.com/paper/1709.06310/) (2017)
- [Learning High-Speed Flight in the Wild](https://mlsanity.com/paper/2110.05113/) (2021)
- [A Comprehensive Survey on Source-free Domain Adaptation](https://mlsanity.com/paper/2302.11803/) (2023)
- [DADA: Depth-aware Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/1904.01886/) (2019)

## Built on by (most cited first, 10 of 10)

- [Perspective-Invariant 3D Object Detection](https://mlsanity.com/paper/2507.17665/) (2025)
- [Talk2Event: Grounded Understanding of Dynamic Scenes from Event Cameras](https://mlsanity.com/paper/2507.17664/) (2025)
- [Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems](https://mlsanity.com/paper/2512.24385/) (2025)
- [Learning to Remove Lens Flare in Event Camera](https://mlsanity.com/paper/2512.09016/) (2025)
- [Scaling Dense Event-Stream Pretraining from Visual Foundation Models](https://mlsanity.com/paper/2603.03969/) (2026)
- [EventDrive: Event Cameras for Vision-Language Driving Intelligence](https://mlsanity.com/paper/2606.18242/) (2026)
- [Visual Grounding from Event Cameras](https://mlsanity.com/paper/2509.09584/) (2025)
- [On The Robustness-Resolution Tradeoff In Temporal Quantization Of Event Streams](https://mlsanity.com/paper/2609.22295/) (2026)
- [Toward On-Chip Training of Spiking Neural Networks for Dense Event-Based Vision](https://mlsanity.com/paper/2609.32405/) (2026)
- [EmbPASS: Towards Cross-Embodiment Open Panoramic Segmentation](https://mlsanity.com/paper/2610.03248/) (2026)

## Abstract (arXiv)

Cross-platform adaptation in event-based dense perception is crucial for deploying event cameras across diverse settings, such as vehicles, drones, and quadrupeds, each with unique motion dynamics, viewpoints, and class distributions. In this work, we introduce EventFly, a framework for robust cross-platform adaptation in event camera perception. Our approach comprises three key components: i) Event Activation Prior (EAP), which identifies high-activation regions in the target domain to minimize prediction entropy, fostering confident, domain-adaptive predictions; ii) EventBlend, a data-mixing strategy that integrates source and target event voxel grids based on EAP-driven similarity and density maps, enhancing feature alignment; and iii) EventMatch, a dual-discriminator technique that aligns features from source, target, and blended domains for better domain-invariant learning. To holistically assess cross-platform adaptation abilities, we introduce EXPo, a large-scale benchmark with diverse samples across vehicle, drone, and quadruped platforms. Extensive experiments validate our effectiveness, demonstrating substantial gains over popular adaptation methods. We hope this work can pave the way for more adaptive, high-performing event perception across diverse and complex environments.