mlsanityData to 7 Oct 2026

SPiKE: 3D Human Pose from Point Cloud Sequences

arXiv 2409.01879 ↗First posted 3 Sep 2024cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

3D Human Pose Estimation (HPE) is the task of locating keypoints of the human body in 3D space from 2D or 3D representations such as RGB images, depth maps or point clouds. Current HPE methods from depth and point clouds predominantly rely on single-frame estimation and do not exploit temporal information from sequences. This paper presents SPiKE, a novel approach to 3D HPE using point cloud sequences. Unlike existing methods that process frames of a sequence independently, SPiKE leverages temporal context by adopting a Transformer architecture to encode spatio-temporal relationships between points across the sequence. By partitioning the point cloud into local volumes and using spatial feature extraction via point spatial convolution, SPiKE ensures efficient processing by the Transformer while preserving spatial integrity per timestamp. Experiments on the ITOP benchmark for 3D HPE show that SPiKE reaches 89.19% mAP, achieving state-of-the-art performance with significantly lower inference times. Extensive ablations further validate the effectiveness of sequence exploitation and our algorithmic choices. Code and models are available at: https://github.com/iballester/SPiKE

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 35 of its 50 references that are in the map. First posted on arXiv 3 Sep 2024.

Builds on

35 of 50 references.

References · 35

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  6. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  7. 2017Sparsity Invariant CNNscited by 325
  8. 2021HuMoR: 3D Human Motion Model for Robust Pose Estimationcited by 319
  9. 2017Submanifold Sparse Convolutional Networkscited by 223
  10. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 220
  11. 2020Deep Learning-Based Human Pose Estimation: A Surveycited by 205
  12. 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 188
23 more
  1. 2020Human Action Recognition from Various Data Modalities: A Reviewcited by 162
  2. 2015Human Pose Estimation with Iterative Error Feedbackcited by 121
  3. 2019MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequencescited by 117
  4. 2019Exploiting temporal context for 3D human pose estimation in the wildcited by 110
  5. 2020Deep Learning for Image and Point Cloud Fusion in Autonomous Driving: A Reviewcited by 107
  6. 2017V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Mapcited by 102
  7. 2023PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimationcited by 91
  8. 2022PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequencescited by 68
  9. 2023MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Networkcited by 62
  10. 2019A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Imagecited by 56
  11. 2022Towards a Deeper Understanding of Skeleton-based Gait Recognitioncited by 55
  12. 20203DV: 3D Dynamic Voxel for Action Recognition in Depth Videocited by 41
  13. 2022Point Primitive Transformer for Long-Term 4D Point Cloud Video Understandingcited by 35
  14. 2022Hierarchical Temporal Transformer for 3D Hand Pose Estimation and Action Recognition from Egocentric RGB Videoscited by 35
  15. 2015Rank Pooling for Action Recognitioncited by 29
  16. 2021DECA: Deep viewpoint-Equivariant human pose estimation using Capsule Autoencoderscited by 23
  17. 2020Forecasting Characteristic 3D Poses of Human Actionscited by 16
  18. 2023LiDAR-HMR: 3D Human Mesh Recovery from LiDARcited by 12
  19. 2022Learning to Estimate 3D Human Pose from Point Cloudcited by 9
  20. 20233D Human Keypoints Estimation From Point Clouds in the Wild Without Human Labelscited by 9
  21. 2023LPFormer: LiDAR Pose Estimation Transformer with Multi-Task Networkcited by 9
  22. 2016Human Pose Estimation from Depth Images via Inference Embedded Multi-task Learningcited by 4
  23. 2023SoloPose: One-Shot Kinematic 3D Human Pose Estimation with Video Data Augmentationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2026Expanding mmWave Datasets for Human Pose Estimation with Unlabeled Data and LiDAR Datasetscited by 1
  2. 2025Point2Pose: A Generative Framework for 3D Human Pose Estimation with Multi-View Point Cloud Datasetcited by 0