# A Real-Time Event-Based Normal Flow Estimator

arXiv: https://arxiv.org/abs/2504.19417 · HTML: https://mlsanity.com/paper/2504.19417/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 22 references that are in the map.
- First posted on arXiv 28 Apr 2025.

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

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Unsupervised Event-based Learning of Optical Flow, Depth, and Egomotion](https://mlsanity.com/paper/1812.08156/) (2018)
- [The Multi Vehicle Stereo Event Camera Dataset: An Event Camera Dataset for 3D Perception](https://mlsanity.com/paper/1801.10202/) (2018)
- [E-RAFT: Dense Optical Flow from Event Cameras](https://mlsanity.com/paper/2108.10552/) (2021)
- [Secrets of Event-Based Optical Flow](https://mlsanity.com/paper/2207.10022/) (2022)
- [EV-IMO: Motion Segmentation Dataset and Learning Pipeline for Event Cameras](https://mlsanity.com/paper/1903.07520/) (2019)
- [EVDodgeNet: Deep Dynamic Obstacle Dodging with Event Cameras](https://mlsanity.com/paper/1906.02919/) (2019)
- [Taming Contrast Maximization for Learning Sequential, Low-latency, Event-based Optical Flow](https://mlsanity.com/paper/2303.05214/) (2023)
- [TMA: Temporal Motion Aggregation for Event-based Optical Flow](https://mlsanity.com/paper/2303.11629/) (2023)
- [EVIMO2: An Event Camera Dataset for Motion Segmentation, Optical Flow, Structure from Motion, and Visual Inertial Odometry in Indoor Scenes with Monocular or Stereo Algorithms](https://mlsanity.com/paper/2205.03467/) (2022)
- [Event-based Visual Inertial Velometer](https://mlsanity.com/paper/2311.18189/) (2023)
- [Motion and Structure from Event-based Normal Flow](https://mlsanity.com/paper/2407.12239/) (2024)
- [Event-Aided Time-to-Collision Estimation for Autonomous Driving](https://mlsanity.com/paper/2407.07324/) (2024)
- [A Linear Time and Space Local Point Cloud Geometry Encoder via Vectorized Kernel Mixture (VecKM)](https://mlsanity.com/paper/2404.01568/) (2024)
- [Learning Normal Flow Directly From Event Neighborhoods](https://mlsanity.com/paper/2412.11284/) (2024)

## Built on by (most cited first, 1 of 1)

- [Real-time Motion Segmentation with Event-based Normal Flow](https://mlsanity.com/paper/2602.20790/) (2026)

## Abstract (arXiv)

This paper presents a real-time, asynchronous, event-based normal flow estimator. It follows the same algorithm as Learning Normal Flow Directly From Event Neighborhoods, but with a more optimized implementation. The original method treats event slices as 3D point clouds, encodes each event's local geometry into a fixed-length vector, and uses a multi-layer perceptron to predict normal flow. It constructs representations by multiplying an adjacency matrix with a feature matrix, resulting in quadratic time complexity with respect to the number of events. In contrast, we leverage the fact that event coordinates are integers and reformulate the representation step as a pooling operation. This achieves the same effect as the adjacency matrix but with much lower computational cost. As a result, our method supports real-time normal flow prediction on event cameras. Our estimator uses 1 GB of CUDA memory and runs at 4 million normal flows per second on an RTX 3070, or 6 million per second on an RTX A5000. We release the CUDA implementation along with a Python interface at https://github.com/dhyuan99/VecKM_flow_cpp.