# Efficient Human Pose Estimation via 3D Event Point Cloud

arXiv: https://arxiv.org/abs/2206.04511 · HTML: https://mlsanity.com/paper/2206.04511/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 72 references that are in the map.
- First posted on arXiv 9 Jun 2022.

## Builds on (most cited first, 30 of 48)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [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)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [Simple Baselines for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1804.06208/) (2018)
- [Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision](https://mlsanity.com/paper/1611.09813/) (2016)
- [LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference](https://mlsanity.com/paper/2104.01136/) (2021)
- [A simple yet effective baseline for 3d human pose estimation](https://mlsanity.com/paper/1705.03098/) (2017)
- [RMPE: Regional Multi-person Pose Estimation](https://mlsanity.com/paper/1612.00137/) (2016)
- [Convolutional Pose Machines](https://mlsanity.com/paper/1602.00134/) (2016)
- [Unsupervised Event-based Learning of Optical Flow, Depth, and Egomotion](https://mlsanity.com/paper/1812.08156/) (2018)
- [DeepPose: Human Pose Estimation via Deep Neural Networks](https://mlsanity.com/paper/1312.4659/) (2013)
- [Integral Human Pose Regression](https://mlsanity.com/paper/1711.08229/) (2017)
- [HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation](https://mlsanity.com/paper/1908.10357/) (2019)
- [EV-FlowNet: Self-Supervised Optical Flow Estimation for Event-based Cameras](https://mlsanity.com/paper/1802.06898/) (2018)
- [End-to-End Learning of Representations for Asynchronous Event-Based Data](https://mlsanity.com/paper/1904.08245/) (2019)
- [CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark](https://mlsanity.com/paper/1812.00324/) (2018)
- [Event-based Vision meets Deep Learning on Steering Prediction for Self-driving Cars](https://mlsanity.com/paper/1804.01310/) (2018)
- [A Unifying Contrast Maximization Framework for Event Cameras, with Applications to Motion, Depth, and Optical Flow Estimation](https://mlsanity.com/paper/1804.01306/) (2018)
- [Panoptic Studio: A Massively Multiview System for Social Interaction Capture](https://mlsanity.com/paper/1612.03153/) (2016)
- [PoseTrack: A Benchmark for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1710.10000/) (2017)
- [Video to Events: Recycling Video Datasets for Event Cameras](https://mlsanity.com/paper/1912.03095/) (2019)
- [Learnable Triangulation of Human Pose](https://mlsanity.com/paper/1905.05754/) (2019)
- [E-RAFT: Dense Optical Flow from Event Cameras](https://mlsanity.com/paper/2108.10552/) (2021)

## Built on by (most cited first, 25 of 25)

- [EventEgo3D: 3D Human Motion Capture from Egocentric Event Streams](https://mlsanity.com/paper/2404.08640/) (2024)
- [A Unified Framework for Event-based Frame Interpolation with Ad-hoc Deblurring in the Wild](https://mlsanity.com/paper/2301.05191/) (2023)
- [Towards Bridging the Space Domain Gap for Satellite Pose Estimation using Event Sensing](https://mlsanity.com/paper/2209.11945/) (2022)
- [Neuromorphic Event-based Facial Expression Recognition](https://mlsanity.com/paper/2304.06351/) (2023)
- [3D Pose Estimation of Two Interacting Hands from a Monocular Event Camera](https://mlsanity.com/paper/2312.14157/) (2023)
- [RELI11D: A Comprehensive Multimodal Human Motion Dataset and Method](https://mlsanity.com/paper/2403.19501/) (2024)
- [NTIRE 2025 Challenge on Event-Based Image Deblurring: Methods and Results](https://mlsanity.com/paper/2504.12401/) (2025)
- [Event-guided Low-light Video Semantic Segmentation](https://mlsanity.com/paper/2411.00639/) (2024)
- [ALERT-Transformer: Bridging Asynchronous and Synchronous Machine Learning for Real-Time Event-based Spatio-Temporal Data](https://mlsanity.com/paper/2402.01393/) (2024)
- [Improving Fast Auto-Focus with Event Polarity](https://mlsanity.com/paper/2303.08611/) (2023)
- [EgoEvGesture: Gesture Recognition Based on Egocentric Event Camera](https://mlsanity.com/paper/2503.12419/) (2025)
- [HFGaussian: Learning Generalizable Gaussian Human with Integrated Human Features](https://mlsanity.com/paper/2411.03086/) (2024)
- [Scalable Event Cloud Network for Event-based Classification](https://mlsanity.com/paper/2412.20803/) (2024)
- [3D Human Scan With A Moving Event Camera](https://mlsanity.com/paper/2404.08504/) (2024)
- [Acoustic-based 3D Human Pose Estimation Robust to Human Position](https://mlsanity.com/paper/2411.07165/) (2024)
- [Event-based Motion Deblurring via Multi-Temporal Granularity Fusion](https://mlsanity.com/paper/2412.11866/) (2024)
- [Exploiting Spatiotemporal Properties for Efficient Event-Driven Human Pose Estimation](https://mlsanity.com/paper/2512.06306/) (2025)
- [EventGait: Towards Robust Gait Recognition with Event Streams](https://mlsanity.com/paper/2605.22139/) (2026)
- [Towards Precise 3D Human Pose Estimation with Multi-Perspective Spatial-Temporal Relational Transformers](https://mlsanity.com/paper/2401.16700/) (2024)
- [EI-Nexus: Towards Unmediated and Flexible Inter-Modality Local Feature Extraction and Matching for Event-Image Data](https://mlsanity.com/paper/2410.21743/) (2024)
- [Helios 2.0: A Robust, Ultra-Low Power Gesture Recognition System Optimised for Event-Sensor based Wearables](https://mlsanity.com/paper/2503.07825/) (2025)
- [OmniEvent: Unified Event Representation Learning](https://mlsanity.com/paper/2508.01842/) (2025)
- [GraphEnet: Event-driven Human Pose Estimation with a Graph Neural Network](https://mlsanity.com/paper/2510.07990/) (2025)
- [FlashCap: Millisecond-Accurate Human Motion Capture via Flashing LEDs and Event-Based Vision](https://mlsanity.com/paper/2603.19770/) (2026)
- [EvDiff: Event-Based Video Reconstruction using One-Step Diffusion Models](https://mlsanity.com/paper/2511.17492/) (2025)

## Abstract (arXiv)

Human Pose Estimation (HPE) based on RGB images has experienced a rapid development benefiting from deep learning. However, event-based HPE has not been fully studied, which remains great potential for applications in extreme scenes and efficiency-critical conditions. In this paper, we are the first to estimate 2D human pose directly from 3D event point cloud. We propose a novel representation of events, the rasterized event point cloud, aggregating events on the same position of a small time slice. It maintains the 3D features from multiple statistical cues and significantly reduces memory consumption and computation complexity, proved to be efficient in our work. We then leverage the rasterized event point cloud as input to three different backbones, PointNet, DGCNN, and Point Transformer, with two linear layer decoders to predict the location of human keypoints. We find that based on our method, PointNet achieves promising results with much faster speed, whereas Point Transfomer reaches much higher accuracy, even close to previous event-frame-based methods. A comprehensive set of results demonstrates that our proposed method is consistently effective for these 3D backbone models in event-driven human pose estimation. Our method based on PointNet with 2048 points input achieves 82.46mm in MPJPE3D on the DHP19 dataset, while only has a latency of 12.29ms on an NVIDIA Jetson Xavier NX edge computing platform, which is ideally suitable for real-time detection with event cameras. Code is available at https://github.com/MasterHow/EventPointPose.