mlsanityData to 14 Oct 2026

Jointformer: Single-Frame Lifting Transformer with Error Prediction and Refinement for 3D Human Pose Estimation

arXiv 2208.03704 ↗First posted 7 Aug 2022cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Monocular 3D human pose estimation technologies have the potential to greatly increase the availability of human movement data. The best-performing models for single-image 2D-3D lifting use graph convolutional networks (GCNs) that typically require some manual input to define the relationships between different body joints. We propose a novel transformer-based approach that uses the more generalised self-attention mechanism to learn these relationships within a sequence of tokens representing joints. We find that the use of intermediate supervision, as well as residual connections between the stacked encoders benefits performance. We also suggest that using error prediction as part of a multi-task learning framework improves performance by allowing the network to compensate for its confidence level. We perform extensive ablation studies to show that each of our contributions increases performance. Furthermore, we show that our approach outperforms the recent state of the art for single-frame 3D human pose estimation by a large margin. Our code and trained models are made publicly available on Github.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 38 of its 49 references that are in the map. First posted on arXiv 7 Aug 2022.

Builds on

38 of 49 references.

References · 38

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2020End-to-End Object Detection with Transformerscited by 7,414
  6. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  7. 2017Non-local Neural Networkscited by 2,293
  8. 2021ViViT: A Video Vision Transformercited by 1,620
  9. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  10. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,162
  11. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
  12. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
26 more
  1. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 494
  2. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 418
  3. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 403
  4. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  5. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  6. 2020Exploring Self-attention for Image Recognitioncited by 313
  7. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 272
  8. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 221
  9. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  10. 2017Compositional Human Pose Regressioncited by 124
  11. 2017Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approachcited by 115
  12. 2020Towards Deeper Graph Neural Networks with Differentiable Group Normalizationcited by 114
  13. 2018Ordinal Depth Supervision for 3D Human Pose Estimationcited by 107
  14. 2021Graph Stacked Hourglass Networks for 3D Human Pose Estimationcited by 95
  15. 2021An Image is Worth 16x16 Words, What is a Video Worth?cited by 87
  16. 20183D Human Pose Estimation in the Wild by Adversarial Learningcited by 86
  17. 2019Monocular 3D Human Pose Estimation by Generation and Ordinal Rankingcited by 76
  18. 20163D Human Pose Estimation from a Single Image via Distance Matrix Regressioncited by 73
  19. 2019HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimationcited by 50
  20. 2017Benchmarking and Error Diagnosis in Multi-Instance Pose Estimationcited by 48
  21. 2018PoseFix: Model-agnostic General Human Pose Refinement Networkcited by 47
  22. 2020Graph-PCNN: Two Stage Human Pose Estimation with Graph Pose Refinementcited by 33
  23. 2018OriNet: A Fully Convolutional Network for 3D Human Pose Estimationcited by 28
  24. 2019Human Pose Estimation with Spatial Contextual Informationcited by 21
  25. 2018Learning to Refine Human Pose Estimationcited by 19
  26. 2019PoseLifter: Absolute 3D human pose lifting network from a single noisy 2D human posecited by 10

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 2; 2024: 3; 2025: 3.

10 papers.

  1. 2022H3WB: Human3.6M 3D WholeBody Dataset and Benchmarkcited by 23
  2. 20233D-LFM: Lifting Foundation Modelcited by 8
  3. 2023Double-chain Constraints for 3D Human Pose Estimation in Images and Videoscited by 4
  4. 2024An Animation-based Augmentation Approach for Action Recognition from Discontinuous Videocited by 2
  5. 2024Quater-GCN: Enhancing 3D Human Pose Estimation with Orientation and Semi-supervised Trainingcited by 2
  6. 2025RAPTR: Radar-based 3D Pose Estimation using Transformercited by 2
  7. 20243D WholeBody Pose Estimation based on Semantic Graph Attention Network and Distance Informationcited by 1
  8. 2025PriorFormer: A Transformer for Real-time Monocular 3D Human Pose Estimation with Versatile Geometric Priorscited by 1
  9. 2022AMPose: Alternately Mixed Global-Local Attention Model for 3D Human Pose Estimationcited by 0
  10. 2025Speak2Sign3D: A Multi-modal Pipeline for English Speech to American Sign Language Animationcited by 0