# v2e: From Video Frames to Realistic DVS Events

arXiv: https://arxiv.org/abs/2006.07722 · HTML: https://mlsanity.com/paper/2006.07722/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jun 2020.

## Built on by (most cited first, 24 of 24)

- [VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows](https://mlsanity.com/paper/2108.05015/) (2021)
- [N-ImageNet: Towards Robust, Fine-Grained Object Recognition with Event Cameras](https://mlsanity.com/paper/2112.01041/) (2021)
- [E-NeRF: Neural Radiance Fields from a Moving Event Camera](https://mlsanity.com/paper/2208.11300/) (2022)
- [Ev-NeRF: Event Based Neural Radiance Field](https://mlsanity.com/paper/2206.12455/) (2022)
- [TUM-VIE: The TUM Stereo Visual-Inertial Event Dataset](https://mlsanity.com/paper/2108.07329/) (2021)
- [Bridging the Gap between Events and Frames through Unsupervised Domain Adaptation](https://mlsanity.com/paper/2109.02618/) (2021)
- [Ev-TTA: Test-Time Adaptation for Event-Based Object Recognition](https://mlsanity.com/paper/2203.12247/) (2022)
- [Feedback control of event cameras](https://mlsanity.com/paper/2105.00409/) (2021)
- [EvDNeRF: Reconstructing Event Data with Dynamic Neural Radiance Fields](https://mlsanity.com/paper/2310.02437/) (2023)
- [Implicit Event-RGBD Neural SLAM](https://mlsanity.com/paper/2311.11013/) (2023)
- [ADV2E: Bridging the Gap Between Analogue Circuit and Discrete Frames in the Video-to-Events Simulator](https://mlsanity.com/paper/2411.12250/) (2024)
- [Event-LSTM: An Unsupervised and Asynchronous Learning-based Representation for Event-based Data](https://mlsanity.com/paper/2105.04216/) (2021)
- [Long-Lived Accurate Keypoints in Event Streams](https://mlsanity.com/paper/2209.10385/) (2022)
- [Self-Supervised Intensity-Event Stereo Matching](https://mlsanity.com/paper/2211.00509/) (2022)
- [ColibriUAV: An Ultra-Fast, Energy-Efficient Neuromorphic Edge Processing UAV-Platform with Event-Based and Frame-Based Cameras](https://mlsanity.com/paper/2305.18371/) (2023)
- [DVS-PedX: Synthetic-and-Real Event-Based Pedestrian Dataset](https://mlsanity.com/paper/2509.04117/) (2025)
- [Event-boosted Deformable 3D Gaussians for Dynamic Scene Reconstruction](https://mlsanity.com/paper/2411.16180/) (2024)
- [Self-Supervised Scene Dynamic Recovery from Rolling Shutter Images and Events](https://mlsanity.com/paper/2304.06930/) (2023)
- [Neuromorphic Seatbelt State Detection for In-Cabin Monitoring with Event Cameras](https://mlsanity.com/paper/2308.07802/) (2023)
- [Event-Based De-Snowing for Autonomous Driving](https://mlsanity.com/paper/2507.20901/) (2025)
- [VibES: Induced Vibration for Persistent Event-Based Sensing](https://mlsanity.com/paper/2508.19094/) (2025)
- [High Throughput Event Filtering: The Interpolation-based DIF Algorithm Hardware Architecture](https://mlsanity.com/paper/2506.05825/) (2025)
- [InterFuserDVS: Event-Enhanced Sensor Fusion for Safe RL-Based Decision Making](https://mlsanity.com/paper/2605.04355/) (2026)
- [A Multimodal RGB and Events Dataset for Hand Detection in First-Person View](https://mlsanity.com/paper/2606.10790/) (2026)

## Abstract (arXiv)

To help meet the increasing need for dynamic vision sensor (DVS) event camera data, this paper proposes the v2e toolbox that generates realistic synthetic DVS events from intensity frames. It also clarifies incorrect claims about DVS motion blur and latency characteristics in recent literature. Unlike other toolboxes, v2e includes pixel-level Gaussian event threshold mismatch, finite intensity-dependent bandwidth, and intensity-dependent noise. Realistic DVS events are useful in training networks for uncontrolled lighting conditions. The use of v2e synthetic events is demonstrated in two experiments. The first experiment is object recognition with N-Caltech 101 dataset. Results show that pretraining on various v2e lighting conditions improves generalization when transferred on real DVS data for a ResNet model. The second experiment shows that for night driving, a car detector trained with v2e events shows an average accuracy improvement of 40% compared to the YOLOv3 trained on intensity frames.