mlsanityData to 7 Oct 2026

Learnable Triangulation of Human Pose

arXiv 1905.05754 ↗First posted 14 May 2019cs.CV cs.AIcited by 160

Not on the map. Why?

Abstract (arXiv)

We present two novel solutions for multi-view 3D human pose estimation based on new learnable triangulation methods that combine 3D information from multiple 2D views. The first (baseline) solution is a basic differentiable algebraic triangulation with an addition of confidence weights estimated from the input images. The second solution is based on a novel method of volumetric aggregation from intermediate 2D backbone feature maps. The aggregated volume is then refined via 3D convolutions that produce final 3D joint heatmaps and allow modelling a human pose prior. Crucially, both approaches are end-to-end differentiable, which allows us to directly optimize the target metric. We demonstrate transferability of the solutions across datasets and considerably improve the multi-view state of the art on the Human3.6M dataset. Video demonstration, annotations and additional materials will be posted on our project page (https://saic-violet.github.io/learnable-triangulation).

Key facts. Cited by 160 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 28; 2022: 28; 2023: 41; 2024: 28; 2025: 21; 2026: 14.

160 papers.

Sort:

By area:

  1. 2022BEHAVE: Dataset and Method for Tracking Human Object Interactionscited by 246
  2. 2021AGORA: Avatars in Geography Optimized for Regression Analysiscited by 203
  3. 2022Capturing and Inferring Dense Full-Body Human-Scene Contactcited by 176
  4. 2021SPEC: Seeing People in the Wild with an Estimated Cameracited by 134
  5. 2022HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modelingcited by 115
  6. 2023Human Motion Generation: A Surveycited by 95
  7. 2022InterCap: Joint Markerless 3D Tracking of Humans and Objects in Interactioncited by 90
  8. 2022KeypointNeRF: Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of Keypointscited by 77
  9. 2021Direct Multi-view Multi-person 3D Pose Estimationcited by 64
  10. 2023AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimationcited by 64
  11. 2023MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Networkcited by 62
  12. 2023EgoHumans: An Egocentric 3D Multi-Human Benchmarkcited by 58
38 more
  1. 2021Conditional Directed Graph Convolution for 3D Human Pose Estimationcited by 52
  2. 2021Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objectscited by 50
  3. 2022UmeTrack: Unified multi-view end-to-end hand tracking for VRcited by 48
  4. 2023GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Videocited by 46
  5. 20233D Human Mesh Estimation from Virtual Markerscited by 44
  6. 2021VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wildcited by 39
  7. 2022Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projectioncited by 39
  8. 2021Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereocited by 38
  9. 2021Context Modeling in 3D Human Pose Estimation: A Unified Perspectivecited by 37
  10. 2023Instant Multi-View Head Capture through Learnable Registrationcited by 34
  11. 2021TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimationcited by 32
  12. 2024Harmony4D: A Video Dataset for In-The-Wild Close Human Interactionscited by 31
  13. 2022The One Where They Reconstructed 3D Humans and Environments in TV Showscited by 30
  14. 2022Scene-aware Egocentric 3D Human Pose Estimationcited by 30
  15. 2021HUMAN4D: A Human-Centric Multimodal Dataset for Motions and Immersive Mediacited by 29
  16. 2022Cross-View Cross-Scene Multi-View Crowd Countingcited by 28
  17. 2022Interaction Replica: Tracking Human-Object Interaction and Scene Changes From Human Motioncited by 27
  18. 2022PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimationcited by 27
  19. 2022Efficient Human Pose Estimation via 3D Event Point Cloudcited by 25
  20. 2021Generalizable Human Pose Triangulationcited by 24
  21. 2021Shape-aware Multi-Person Pose Estimation from Multi-View Imagescited by 24
  22. 2023Back to Optimization: Diffusion-based Zero-Shot 3D Human Pose Estimationcited by 24
  23. 2023HDFormer: High-order Directed Transformer for 3D Human Pose Estimationcited by 23
  24. 2024Look Ma, no markers: holistic performance capture without the hasslecited by 23
  25. 2023TEMPO: Efficient Multi-View Pose Estimation, Tracking, and Forecastingcited by 22
  26. 2023Ego3DPose: Capturing 3D Cues from Binocular Egocentric Viewscited by 22
  27. 2024SelfPose3d: Self-Supervised Multi-Person Multi-View 3d Pose Estimationcited by 21
  28. 2023Vision-Based Human Pose Estimation via Deep Learning: A Surveycited by 20
  29. 2024A Comprehensive Survey of Action Quality Assessment: Method and Benchmarkcited by 20
  30. 2021Adaptive Multi-view and Temporal Fusing Transformer for 3D Human Pose Estimationcited by 19
  31. 2023Multiple View Geometry Transformers for 3D Human Pose Estimationcited by 19
  32. 2022Efficient Annotation and Learning for 3D Hand Pose Estimation: A Surveycited by 17
  33. 2023Fusing Monocular Images and Sparse IMU Signals for Real-time Human Motion Capturecited by 17
  34. 2024ExpertAF: Expert Actionable Feedback from Videocited by 17
  35. 2022Learnable human mesh triangulation for 3D human pose and shape estimationcited by 16
  36. 2023Novel-view Synthesis and Pose Estimation for Hand-Object Interaction from Sparse Viewscited by 16
  37. 2024AutoSoccerPose: Automated 3D posture Analysis of Soccer Shot Movementscited by 15
  38. 2021TrajeVAE: Controllable Human Motion Generation from Trajectoriescited by 14

50 most cited of 160 All 160 (JSON)