# Learning Normal Flow Directly From Event Neighborhoods

arXiv: https://arxiv.org/abs/2412.11284 · HTML: https://mlsanity.com/paper/2412.11284/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 64 references that are in the map.
- First posted on arXiv 15 Dec 2024.

## Builds on (most cited first, 30 of 44)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework](https://mlsanity.com/paper/2202.07123/) (2022)
- [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)
- [EV-FlowNet: Self-Supervised Optical Flow Estimation for Event-based Cameras](https://mlsanity.com/paper/1802.06898/) (2018)
- [Deep Complex Networks](https://mlsanity.com/paper/1705.09792/) (2017)
- [A Unifying Contrast Maximization Framework for Event Cameras, with Applications to Motion, Depth, and Optical Flow Estimation](https://mlsanity.com/paper/1804.01306/) (2018)
- [E-RAFT: Dense Optical Flow from Event Cameras](https://mlsanity.com/paper/2108.10552/) (2021)
- [Modeling Point Clouds with Self-Attention and Gumbel Subset Sampling](https://mlsanity.com/paper/1904.03375/) (2019)
- [Self-Supervised Learning of Event-Based Optical Flow with Spiking Neural Networks](https://mlsanity.com/paper/2106.01862/) (2021)
- [Secrets of Event-Based Optical Flow](https://mlsanity.com/paper/2207.10022/) (2022)
- [Learning Dense and Continuous Optical Flow from an Event Camera](https://mlsanity.com/paper/2211.09078/) (2022)
- [EventNet: Asynchronous Recursive Event Processing](https://mlsanity.com/paper/1812.07045/) (2018)
- [Dense Continuous-Time Optical Flow from Events and Frames](https://mlsanity.com/paper/2203.13674/) (2022)
- [Taming Contrast Maximization for Learning Sequential, Low-latency, Event-based Optical Flow](https://mlsanity.com/paper/2303.05214/) (2023)
- [Optical flow estimation from event-based cameras and spiking neural networks](https://mlsanity.com/paper/2302.06492/) (2023)
- [BlinkFlow: A Dataset to Push the Limits of Event-based Optical Flow Estimation](https://mlsanity.com/paper/2303.07716/) (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)
- [Lightweight Event-based Optical Flow Estimation via Iterative Deblurring](https://mlsanity.com/paper/2211.13726/) (2022)
- [SpikePoint: An Efficient Point-based Spiking Neural Network for Event Cameras Action Recognition](https://mlsanity.com/paper/2310.07189/) (2023)
- [Distance Surface for Event-Based Optical Flow](https://mlsanity.com/paper/2003.12680/) (2020)
- [Real-Time Optical Flow for Vehicular Perception with Low- and High-Resolution Event Cameras](https://mlsanity.com/paper/2112.10591/) (2021)
- [DiffPoseNet: Direct Differentiable Camera Pose Estimation](https://mlsanity.com/paper/2203.11174/) (2022)
- [Learning Optical Flow from Event Camera with Rendered Dataset](https://mlsanity.com/paper/2303.11011/) (2023)
- [RPEFlow: Multimodal Fusion of RGB-PointCloud-Event for Joint Optical Flow and Scene Flow Estimation](https://mlsanity.com/paper/2309.15082/) (2023)
- [Real-time high speed motion prediction using fast aperture-robust event-driven visual flow](https://mlsanity.com/paper/1811.11135/) (2018)
- [Repurposing Pre-trained Video Diffusion Models for Event-based Video Interpolation](https://mlsanity.com/paper/2412.07761/) (2024)

## Built on by (most cited first, 5 of 5)

- [EV-Flying: an Event-based Dataset for In-The-Wild Recognition of Flying Objects](https://mlsanity.com/paper/2506.04048/) (2025)
- [Minimal Solvers for Full DoF Motion Estimation from Asynchronous Tracks](https://mlsanity.com/paper/2508.17537/) (2025)
- [A Real-Time Event-Based Normal Flow Estimator](https://mlsanity.com/paper/2504.19417/) (2025)
- [Real-time Motion Segmentation with Event-based Normal Flow](https://mlsanity.com/paper/2602.20790/) (2026)
- [LC-Flow: Learning Local Continuous Optical Flow and Confidence from events](https://mlsanity.com/paper/2605.24604/) (2026)

## Abstract (arXiv)

Event-based motion field estimation is an important task. However, current optical flow methods face challenges: learning-based approaches, often frame-based and relying on CNNs, lack cross-domain transferability, while model-based methods, though more robust, are less accurate. To address the limitations of optical flow estimation, recent works have focused on normal flow, which can be more reliably measured in regions with limited texture or strong edges. However, existing normal flow estimators are predominantly model-based and suffer from high errors. In this paper, we propose a novel supervised point-based method for normal flow estimation that overcomes the limitations of existing event learning-based approaches. Using a local point cloud encoder, our method directly estimates per-event normal flow from raw events, offering multiple unique advantages: 1) It produces temporally and spatially sharp predictions. 2) It supports more diverse data augmentation, such as random rotation, to improve robustness across various domains. 3) It naturally supports uncertainty quantification via ensemble inference, which benefits downstream tasks. 4) It enables training and inference on undistorted data in normalized camera coordinates, improving transferability across cameras. Extensive experiments demonstrate our method achieves better and more consistent performance than state-of-the-art methods when transferred across different datasets. Leveraging this transferability, we train our model on the union of datasets and release it for public use. Finally, we introduce an egomotion solver based on a maximum-margin problem that uses normal flow and IMU to achieve strong performance in challenging scenarios.