mlsanityData to 14 Oct 2026

PifPaf: Composite Fields for Human Pose Estimation

arXiv 1903.06593 ↗First posted 15 Mar 2019cs.CVcited by 120

Not on the map. Why?

Abstract (arXiv)

We propose a new bottom-up method for multi-person 2D human pose estimation that is particularly well suited for urban mobility such as self-driving cars and delivery robots. The new method, PifPaf, uses a Part Intensity Field (PIF) to localize body parts and a Part Association Field (PAF) to associate body parts with each other to form full human poses. Our method outperforms previous methods at low resolution and in crowded, cluttered and occluded scenes thanks to (i) our new composite field PAF encoding fine-grained information and (ii) the choice of Laplace loss for regressions which incorporates a notion of uncertainty. Our architecture is based on a fully convolutional, single-shot, box-free design. We perform on par with the existing state-of-the-art bottom-up method on the standard COCO keypoint task and produce state-of-the-art results on a modified COCO keypoint task for the transportation domain.

Key facts. Cited by 120 papers in the map (data through 14 Oct 2026). First posted on arXiv 15 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 35; 2022: 32; 2023: 22; 2024: 17; 2025: 9; 2026: 5.

120 papers.

Sort:

By area:

  1. 2022AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Timecited by 200
  2. 2023RTMPose: Real-Time Multi-Person Pose Estimation based on MMPosecited by 175
  3. 2021Putting People in their Place: Monocular Regression of 3D People in Depthcited by 142
  4. 2021Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regressioncited by 112
  5. 2021Pose Recognition with Cascade Transformerscited by 99
  6. 2022YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Losscited by 68
  7. 2022ViTPose++: Vision Transformer for Generic Body Pose Estimationcited by 65
  8. 2021Direct Multi-view Multi-person 3D Pose Estimationcited by 64
  9. 2022Body Part-Based Representation Learning for Occluded Person Re-Identificationcited by 64
  10. 2021OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Associationcited by 55
  11. 2021Deep Dual Consecutive Network for Human Pose Estimationcited by 51
  12. 2021Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspectivecited by 50
38 more
  1. 2021When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarkscited by 41
  2. 2021VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wildcited by 39
  3. 2021FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutionscited by 34
  4. 2021Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsingcited by 31
  5. 2021Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimationcited by 30
  6. 2021End-to-End Trainable Multi-Instance Pose Estimation with Transformerscited by 30
  7. 2023Group Pose: A Simple Baseline for End-to-End Multi-person Pose Estimationcited by 26
  8. 2022Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimationcited by 24
  9. 2023Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Predictioncited by 23
  10. 2021PandaNet : Anchor-Based Single-Shot Multi-Person 3D Pose Estimationcited by 22
  11. 20222D Human Pose Estimation: A Surveycited by 21
  12. 2024SelfPose3d: Self-Supervised Multi-Person Multi-View 3d Pose Estimationcited by 21
  13. 2021Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimationcited by 20
  14. 2021The Center of Attention: Center-Keypoint Grouping via Attention for Multi-Person Pose Estimationcited by 18
  15. 2023Reconstructing Groups of People with Hypergraph Relational Reasoningcited by 18
  16. 2023Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Videocited by 17
  17. 2022Lite Pose: Efficient Architecture Design for 2D Human Pose Estimationcited by 16
  18. 2021Fusion-GCN: Multimodal Action Recognition using Graph Convolutional Networkscited by 15
  19. 2021Learning Local-Global Contextual Adaptation for Multi-Person Pose Estimationcited by 14
  20. 2022Jointly Harnessing Prior Structures and Temporal Consistency for Sign Language Video Generationcited by 14
  21. 2022PoseTrans: A Simple Yet Effective Pose Transformation Augmentation for Human Pose Estimationcited by 14
  22. 2021InsPose: Instance-Aware Networks for Single-Stage Multi-Person Pose Estimationcited by 13
  23. 2022Dual networks based 3D Multi-Person Pose Estimation from Monocular Videocited by 13
  24. 2022QueryPose: Sparse Multi-Person Pose Regression via Spatial-Aware Part-Level Querycited by 13
  25. 2023Prior-guided Source-free Domain Adaptation for Human Pose Estimationcited by 13
  26. 2022Deep Learning-based Occluded Person Re-identification: A Surveycited by 12
  27. 2022Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Taskscited by 12
  28. 2024SHIC: Shape-Image Correspondences with no Keypoint Supervisioncited by 12
  29. 2021DeepSportLab: a Unified Framework for Ball Detection, Player Instance Segmentation and Pose Estimation in Team Sports Scenescited by 11
  30. 2022Coverage-Guided Tensor Compiler Fuzzing with Joint IR-Pass Mutationcited by 10
  31. 2022Explicit Occlusion Reasoning for Multi-person 3D Human Pose Estimationcited by 10
  32. 2024Video-Based Human Pose Regression via Decoupled Space-Time Aggregationcited by 10
  33. 2021Unsupervised 3D Pose Estimation for Hierarchical Dance Video Recognitioncited by 9
  34. 2022Dynamic Graph Reasoning for Multi-person 3D Pose Estimationcited by 9
  35. 2022VL4Pose: Active Learning Through Out-Of-Distribution Detection For Pose Estimationcited by 9
  36. 2021Keypoint Communitiescited by 8
  37. 2021End-to-End Hierarchical Relation Extraction for Generic Form Understandingcited by 7
  38. 2021Unsupervised domain adaptation for clinician pose estimation and instance segmentation in the operating roomcited by 7

50 most cited of 120 All 120 (JSON)