mlsanityData to 14 Oct 2026

TEMPO: Efficient Multi-View Pose Estimation, Tracking, and Forecasting

arXiv 2309.07910 ↗First posted 14 Sep 2023cs.CVcited by 22

Not on the map. Why?

Abstract (arXiv)

Existing volumetric methods for predicting 3D human pose estimation are accurate, but computationally expensive and optimized for single time-step prediction. We present TEMPO, an efficient multi-view pose estimation model that learns a robust spatiotemporal representation, improving pose accuracy while also tracking and forecasting human pose. We significantly reduce computation compared to the state-of-the-art by recurrently computing per-person 2D pose features, fusing both spatial and temporal information into a single representation. In doing so, our model is able to use spatiotemporal context to predict more accurate human poses without sacrificing efficiency. We further use this representation to track human poses over time as well as predict future poses. Finally, we demonstrate that our model is able to generalize across datasets without scene-specific fine-tuning. TEMPO achieves 10% better MPJPE with a 33× improvement in FPS compared to TesseTrack on the challenging CMU Panoptic Studio dataset.

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). Builds on 40 of its 57 references that are in the map. First posted on arXiv 14 Sep 2023.

Builds on

40 of 57 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2022A ConvNet for the 2020scited by 3,579
  3. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  4. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  5. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,218
  6. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,044
  7. 2017End-to-end Recovery of Human Shape and Posecited by 885
  8. 2016Simple Online and Realtime Trackingcited by 868
  9. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 695
  10. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 620
  11. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  12. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 405
28 more
  1. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  2. 2019Learning Trajectory Dependencies for Human Motion Predictioncited by 246
  3. 2021FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Camerascited by 239
  4. 2020Monocular, One-stage, Regression of Multiple 3D Peoplecited by 218
  5. 2022Particle Video Revisited: Tracking Through Occlusions Using Point Trajectoriescited by 217
  6. 2020Long-term Human Motion Prediction with Scene Contextcited by 192
  7. 2022Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detectioncited by 178
  8. 2019Learnable Triangulation of Human Posecited by 161
  9. 2015Delving Deeper into Convolutional Networks for Learning Video Representationscited by 148
  10. 2022Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?cited by 128
  11. 2020Epipolar Transformerscited by 117
  12. 2017V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Mapcited by 102
  13. 2019Cross View Fusion for 3D Human Pose Estimationcited by 90
  14. 2019Fast and Robust Multi-Person 3D Pose Estimation from Multiple Viewscited by 83
  15. 2023EgoHumans: An Egocentric 3D Multi-Human Benchmarkcited by 60
  16. 20204D Association Graph for Realtime Multi-person Motion Capture Using Multiple Video Camerascited by 49
  17. 2017Harvesting Multiple Views for Marker-less 3D Human Pose Annotationscited by 48
  18. 2021VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wildcited by 39
  19. 2022Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projectioncited by 39
  20. 2021Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereocited by 38
  21. 2021Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Imagescited by 38
  22. 2018Learning Spatial Common Sense with Geometry-Aware Recurrent Networkscited by 35
  23. 2022PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimationcited by 27
  24. 2018A generalizable approach for multi-view 3D human pose regressioncited by 26
  25. 2021Shape-aware Multi-Person Pose Estimation from Multi-View Imagescited by 24
  26. 2021Tracking People with 3D Representationscited by 22
  27. 2021Real-Time Multi-View 3D Human Pose Estimation using Semantic Feedback to Smart Edge Sensorscited by 16
  28. 2022Snipper: A Spatiotemporal Transformer for Simultaneous Multi-Person 3D Pose Estimation Tracking and Forecasting on a Video Snippetcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 8; 2025: 6; 2026: 7.

22 papers.

Sort:

By area:

  1. 2024MotionChain: Conversational Motion Controllers via Multimodal Promptscited by 30
  2. 2024Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioningcited by 30
  3. 2024Look Ma, no markers: holistic performance capture without the hasslecited by 23
  4. 2024SelfPose3d: Self-Supervised Multi-Person Multi-View 3d Pose Estimationcited by 21
  5. 2025The Invisible EgoHand: 3D Hand Forecasting through EgoBody Pose Estimationcited by 16
  6. 2025WorldPose: A World Cup Dataset for Global 3D Human Pose Estimationcited by 14
  7. 2024EgoCast: Forecasting Egocentric Human Pose in the Wildcited by 11
  8. 2024AvatarPose: Avatar-guided 3D Pose Estimation of Close Human Interaction from Sparse Multi-view Videoscited by 7
  9. 2023Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Surveycited by 6
  10. 2024CondiMen: Conditional Multi-Person Mesh Recoverycited by 5
  11. 2024VoxelKeypointFusion: Generalizable Multi-View Multi-Person Pose Estimationcited by 3
  12. 2025Every Angle Is Worth A Second Glance: Mining Kinematic Skeletal Structures from Multi-view Joint Cloudcited by 2
10 more
  1. 2025RapidPoseTriangulation: Multi-view Multi-person Whole-body Human Pose Triangulation in a Millisecondcited by 2
  2. 2025SimpleDepthPose: Fast and Reliable Human Pose Estimation with RGBD-Imagescited by 1
  3. 2026COMPOSE: Hypergraph Cover Optimization for Multi-view 3D Human Pose Estimationcited by 1
  4. 2026Learning Context-Adaptive Motion Priors for Masked Motion Diffusion Models with Efficient Kinematic Attention Aggregationcited by 1
  5. 2026Ego-Human Motion Prediction with 3D-Aware LLMcited by 1
  6. 2025DKPMV: Dense Keypoints Fusion from Multi-View RGB Frames for 6D Pose Estimation of Textureless Objectscited by 0
  7. 2026Garment Inertial Denoiser (GID): Endowing Accurate Motion Capture via Loose IMU Denoisercited by 0
  8. 2026DisPOSE: Projected Polystochastic Diffusion for Self-Supervised Multi-View 3D Human Pose Estimationcited by 0
  9. 2026MVDGC: Joint 3D and 2D Multi-view Pedestrian Detection via Dual Geometric Constraintscited by 0
  10. 2026STA-TFM: Spatio-Temporal Aggregation Across Views TransForMer for Pose Estimationcited by 0