mlsanityData to 14 Oct 2026

EventHPE: Event-based 3D Human Pose and Shape Estimation

arXiv 2108.06819 ↗First posted 15 Aug 2021cs.CVcited by 42

Not on the map. Why?

Abstract (arXiv)

Event camera is an emerging imaging sensor for capturing dynamics of moving objects as events, which motivates our work in estimating 3D human pose and shape from the event signals. Events, on the other hand, have their unique challenges: rather than capturing static body postures, the event signals are best at capturing local motions. This leads us to propose a two-stage deep learning approach, called EventHPE. The first-stage, FlowNet, is trained by unsupervised learning to infer optical flow from events. Both events and optical flow are closely related to human body dynamics, which are fed as input to the ShapeNet in the second stage, to estimate 3D human shapes. To mitigate the discrepancy between image-based flow (optical flow) and shape-based flow (vertices movement of human body shape), a novel flow coherence loss is introduced by exploiting the fact that both flows are originated from the identical human motion. An in-house event-based 3D human dataset is curated that comes with 3D pose and shape annotations, which is by far the largest one to our knowledge. Empirical evaluations on DHP19 dataset and our in-house dataset demonstrate the effectiveness of our approach.

Key facts. Cited by 42 papers in the map (data through 14 Oct 2026). Builds on 28 of its 36 references that are in the map. First posted on arXiv 15 Aug 2021.

Builds on

28 of 36 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  4. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  5. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,162
  6. 2019Event-based Vision: A Surveycited by 1,016
  7. 2017End-to-end Recovery of Human Shape and Posecited by 885
  8. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 784
  9. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 620
  10. 2018Learning 3D Human Dynamics from Videocited by 316
  11. 2018Learning to Estimate 3D Human Pose and Shape from a Single Color Imagecited by 226
  12. 2018EV-FlowNet: Self-Supervised Optical Flow Estimation for Event-based Camerascited by 224
16 more
  1. 2019End-to-End Learning of Representations for Asynchronous Event-Based Datacited by 217
  2. 2018Asynchronous, Photometric Feature Tracking using Events and Framescited by 118
  3. 20163D Human Pose Estimation = 2D Pose Estimation + Matchingcited by 113
  4. 2019DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-Comparecited by 100
  5. 2020Learning Event-Based Motion Deblurringcited by 81
  6. 2019EventCap: Monocular 3D Capture of High-Speed Human Motions using an Event Cameracited by 65
  7. 2015Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Videocited by 54
  8. 2016Event-based, 6-DOF Camera Tracking from Photometric Depth Mapscited by 54
  9. 2018A Progressive Batching L-BFGS Method for Machine Learningcited by 45
  10. 2015Maximum-Margin Structured Learning with Deep Networks for 3D Human Pose Estimationcited by 37
  11. 20163D Human Pose Estimation Using Convolutional Neural Networks with 2D Pose Informationcited by 28
  12. 2014Robust Estimation of 3D Human Poses from a Single Imagecited by 23
  13. 20193D Human Pose Machines with Self-supervised Learningcited by 17
  14. 2020SparseFusion: Dynamic Human Avatar Modeling from Sparse RGBD Imagescited by 16
  15. 2021Detailed Avatar Recovery from Single Imagecited by 16
  16. 2016A Simple, Fast and Highly-Accurate Algorithm to Recover 3D Shape from 2D Landmarks on a Single Imagecited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 7; 2023: 9; 2024: 9; 2025: 14; 2026: 3.

42 papers.

Sort:

By area:

  1. 2022EventNeRF: Neural Radiance Fields from a Single Colour Event Cameracited by 92
  2. 2023Deep Learning for Event-based Vision: A Comprehensive Survey and Benchmarkscited by 90
  3. 2024Recent Event Camera Innovations: A Surveycited by 68
  4. 2022State of the Art in Dense Monocular Non-Rigid 3D Reconstructioncited by 30
  5. 2024EventEgo3D: 3D Human Motion Capture from Egocentric Event Streamscited by 29
  6. 2022Efficient Human Pose Estimation via 3D Event Point Cloudcited by 25
  7. 20222D Human Pose Estimation: A Surveycited by 21
  8. 2023EvHandPose: Event-based 3D Hand Pose Estimation with Sparse Supervisioncited by 17
  9. 2024Microsaccade-inspired Event Camera for Roboticscited by 17
  10. 2024RELI11D: A Comprehensive Multimodal Human Motion Dataset and Methodcited by 16
  11. 2024Complementing Event Streams and RGB Frames for Hand Mesh Reconstructioncited by 14
  12. 2023A Hybrid ANN-SNN Architecture for Low-Power and Low-Latency Visual Perceptioncited by 13
30 more
  1. 2023Highly Efficient 3D Human Pose Tracking from Events with Spiking Spatiotemporal Transformercited by 10
  2. 2023Neuromorphic High-Frequency 3D Dancing Pose Estimation in Dynamic Environmentcited by 8
  3. 2023Lightweight Super-Resolution Head for Human Pose Estimationcited by 7
  4. 2025E-4DGS: High-Fidelity Dynamic Reconstruction from the Multi-view Event Camerascited by 7
  5. 2024GTPT: Group-based Token Pruning Transformer for Efficient Human Pose Estimationcited by 6
  6. 2025EventEgo3D++: 3D Human Motion Capture from a Head-Mounted Event Cameracited by 6
  7. 2025Event Camera Meets Mobile Embodied Perception: Abstraction, Algorithm, Acceleration, Applicationcited by 6
  8. 2022A Temporal Densely Connected Recurrent Network for Event-based Human Pose Estimationcited by 5
  9. 2025EventEgoHands: Event-based Egocentric 3D Hand Mesh Reconstructioncited by 5
  10. 2023Exploring Event-based Human Pose Estimation with 3D Event Representationscited by 4
  11. 2024Dynamic EventNeRF: Reconstructing General Dynamic Scenes from Multi-view RGB and Event Streamscited by 4
  12. 2025EgoEvGesture: Gesture Recognition Based on Egocentric Event Cameracited by 4
  13. 2025SpikeVideoFormer: An Efficient Spike-Driven Video Transformer with Hamming Attention and O(T) Complexitycited by 4
  14. 2025Hardware, Algorithms, and Applications of the Neuromorphic Vision Sensor: a Reviewcited by 3
  15. 2025From Sharp to Blur: Unsupervised Domain Adaptation for 2D Human Pose Estimation Under Extreme Motion Blur Using Event Camerascited by 3
  16. 2023Sparse and Privacy-enhanced Representation for Human Pose Estimationcited by 2
  17. 20243D Human Scan With A Moving Event Cameracited by 2
  18. 2025Exploiting Spatiotemporal Properties for Efficient Event-Driven Human Pose Estimationcited by 2
  19. 2022Bootstrapping Human Optical Flow and Posecited by 1
  20. 2023EvPlug: Learn a Plug-and-Play Module for Event and Image Fusioncited by 1
  21. 2024ExFMan: Rendering 3D Dynamic Humans with Hybrid Monocular Blurry Frames and Eventscited by 1
  22. 2025Unveiling Hidden Vulnerabilities in Digital Human Generation via Adversarial Attackscited by 1
  23. 2025ControlEvents: Controllable Synthesis of Event Camera Datawith Foundational Prior from Image Diffusion Modelscited by 1
  24. 2025GraphEnet: Event-driven Human Pose Estimation with a Graph Neural Networkcited by 1
  25. 2026FlashCap: Millisecond-Accurate Human Motion Capture via Flashing LEDs and Event-Based Visioncited by 1
  26. 2026E-3DPSM: A State Machine for Event-Based Egocentric 3D Human Pose Estimationcited by 1
  27. 2022Spatio-temporal Tendency Reasoning for Human Body Pose and Shape Estimation from Videoscited by 0
  28. 2025LatentStealth: Unnoticeable and Efficient Adversarial Attacks on Expressive Human Pose and Shape Estimationcited by 0
  29. 2025Event-guided 3D Gaussian Splatting for Dynamic Human and Scene Reconstructioncited by 0
  30. 2026EventNeuS: 3D Mesh Reconstruction from a Single Event Cameracited by 0