# Real-time Motion Segmentation with Event-based Normal Flow

arXiv: https://arxiv.org/abs/2602.20790 · HTML: https://mlsanity.com/paper/2602.20790/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 38 references that are in the map.
- First posted on arXiv 24 Feb 2026.

## Builds on (most cited first, 23 of 23)

- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [A Unifying Contrast Maximization Framework for Event Cameras, with Applications to Motion, Depth, and Optical Flow Estimation](https://mlsanity.com/paper/1804.01306/) (2018)
- [Ultimate SLAM? Combining Events, Images, and IMU for Robust Visual SLAM in HDR and High Speed Scenarios](https://mlsanity.com/paper/1709.06310/) (2017)
- [Event-based Moving Object Detection and Tracking](https://mlsanity.com/paper/1803.04523/) (2018)
- [Focus Is All You Need: Loss Functions For Event-based Vision](https://mlsanity.com/paper/1904.07235/) (2019)
- [Learning Dense and Continuous Optical Flow from an Event Camera](https://mlsanity.com/paper/2211.09078/) (2022)
- [Event-based Motion Segmentation with Spatio-Temporal Graph Cuts](https://mlsanity.com/paper/2012.08730/) (2020)
- [EV-IMO: Motion Segmentation Dataset and Learning Pipeline for Event Cameras](https://mlsanity.com/paper/1903.07520/) (2019)
- [Deep Event Visual Odometry](https://mlsanity.com/paper/2312.09800/) (2023)
- [DiffPoseNet: Direct Differentiable Camera Pose Estimation](https://mlsanity.com/paper/2203.11174/) (2022)
- [Real-time high speed motion prediction using fast aperture-robust event-driven visual flow](https://mlsanity.com/paper/1811.11135/) (2018)
- [ESVO2: Direct Visual-Inertial Odometry with Stereo Event Cameras](https://mlsanity.com/paper/2410.09374/) (2024)
- [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)
- [Event-based Motion Segmentation by Cascaded Two-Level Multi-Model Fitting](https://mlsanity.com/paper/2111.03483/) (2021)
- [JSTR: Joint Spatio-Temporal Reasoning for Event-based Moving Object Detection](https://mlsanity.com/paper/2403.07436/) (2024)
- [A Linear Time and Space Local Point Cloud Geometry Encoder via Vectorized Kernel Mixture (VecKM)](https://mlsanity.com/paper/2404.01568/) (2024)
- [Instance-Level Moving Object Segmentation from a Single Image with Events](https://mlsanity.com/paper/2502.12975/) (2025)
- [FAITH: Fast iterative half-plane focus of expansion estimation using event-based optic flow](https://mlsanity.com/paper/2102.12823/) (2021)
- [Learning Normal Flow Directly From Event Neighborhoods](https://mlsanity.com/paper/2412.11284/) (2024)
- [0-MMS: Zero-Shot Multi-Motion Segmentation With A Monocular Event Camera](https://mlsanity.com/paper/2006.06158/) (2020)
- [A Real-Time Event-Based Normal Flow Estimator](https://mlsanity.com/paper/2504.19417/) (2025)

## Abstract (arXiv)

Event-based cameras are bio-inspired sensors with pixels that independently and asynchronously respond to brightness changes at microsecond resolution, offering the potential to handle visual tasks in challenging scenarios. However, due to the sparse information content in individual events, directly processing the raw event data to solve vision tasks is highly inefficient, which severely limits the applicability of state-of-the-art methods in real-time tasks, such as motion segmentation, a fundamental task for dynamic scene understanding. Incorporating normal flow as an intermediate representation to compress motion information from event clusters within a localized region provides a more effective solution. In this work, we propose a normal flow-based motion segmentation framework for event-based vision. Leveraging the dense normal flow directly learned from event neighborhoods as input, we formulate the motion segmentation task as an energy minimization problem solved via graph cuts, and optimize it iteratively with normal flow clustering and motion model fitting. By using a normal flow-based motion model initialization and fitting method, the proposed system is able to efficiently estimate the motion models of independently moving objects with only a limited number of candidate models, which significantly reduces the computational complexity and ensures real-time performance, achieving nearly a 800x speedup in comparison to the open-source state-of-the-art method. Extensive evaluations on multiple public datasets fully demonstrate the accuracy and efficiency of our framework.