mlsanityData to 7 Oct 2026

A Single 2D Pose with Context is Worth Hundreds for 3D Human Pose Estimation

arXiv 2311.03312 ↗First posted 6 Nov 2023cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

The dominant paradigm in 3D human pose estimation that lifts a 2D pose sequence to 3D heavily relies on long-term temporal clues (i.e., using a daunting number of video frames) for improved accuracy, which incurs performance saturation, intractable computation and the non-causal problem. This can be attributed to their inherent inability to perceive spatial context as plain 2D joint coordinates carry no visual cues. To address this issue, we propose a straightforward yet powerful solution: leveraging the readily available intermediate visual representations produced by off-the-shelf (pre-trained) 2D pose detectors -- no finetuning on the 3D task is even needed. The key observation is that, while the pose detector learns to localize 2D joints, such representations (e.g., feature maps) implicitly encode the joint-centric spatial context thanks to the regional operations in backbone networks. We design a simple baseline named Context-Aware PoseFormer to showcase its effectiveness. Without access to any temporal information, the proposed method significantly outperforms its context-agnostic counterpart, PoseFormer, and other state-of-the-art methods using up to hundreds of video frames regarding both speed and precision. Project page: https://qitaozhao.github.io/ContextAware-PoseFormer

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 61 of its 78 references that are in the map. First posted on arXiv 6 Nov 2023.

Builds on

61 of 78 references.

References · 61

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  6. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  8. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  9. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  10. 2017Deformable Convolutional Networkscited by 1,481
  11. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  12. 2019VisualBERT: A Simple and Performant Baseline for Vision and Languagecited by 1,291
38 more
  1. 2021ViLT: Vision-and-Language Transformer Without Convolution or Region Supervisioncited by 1,224
  2. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,148
  3. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  4. 2021Multiscale Vision Transformerscited by 896
  5. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  6. 2019VideoBERT: A Joint Model for Video and Language Representation Learningcited by 702
  7. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  8. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  9. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 450
  10. 2021VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Expertscited by 424
  11. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
  12. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  13. 2021Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognitioncited by 317
  14. 2023Effective Whole-body Pose Estimation with Two-stages Distillationcited by 307
  15. 2019NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detectioncited by 289
  16. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 271
  17. 2017Integral Human Pose Regressioncited by 255
  18. 2021PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loopcited by 250
  19. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
  20. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 220
  21. 2020Deep Learning-Based Human Pose Estimation: A Surveycited by 205
  22. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  23. 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 158
  24. 2021MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimationcited by 151
  25. 2017VNect: Real-time 3D Human Pose Estimation with a Single RGB Cameracited by 129
  26. 2023One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformercited by 128
  27. 20163D Human Pose Estimation = 2D Pose Estimation + Matchingcited by 112
  28. 2018Ordinal Depth Supervision for 3D Human Pose Estimationcited by 107
  29. 2020SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approachcited by 94
  30. 2021Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimationcited by 94
  31. 2021Graph Stacked Hourglass Networks for 3D Human Pose Estimationcited by 94
  32. 2023PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimationcited by 91
  33. 2020Motion Guided 3D Pose Estimation from Videoscited by 85
  34. 2021Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flowscited by 84
  35. 2020Cascaded deep monocular 3D human pose estimation with evolutionary training datacited by 80
  36. 2022P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimationcited by 80
  37. 20163D Human Pose Estimation from a Single Image via Distance Matrix Regressioncited by 73
  38. 2021Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimationcited by 62

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 7; 2026: 2.

11 papers.

  1. 2025Web-Scale Collection of Video Data for 4D Animal Reconstructioncited by 8
  2. 2025DiSRT-In-Bed: Diffusion-Based Sim-to-Real Transfer Framework for In-Bed Human Mesh Recoverycited by 6
  3. 2025AnyMoLe: Any Character Motion In-betweening Leveraging Video Diffusion Modelscited by 4
  4. 2024Di2Pose: Discrete Diffusion Model for Occluded 3D Human Pose Estimationcited by 2
  5. 2024BLAPose: Enhancing 3D Human Pose Estimation with Bone Length Adjustmentcited by 2
  6. 2025Human Motion Prediction via Test-domain-aware Adaptation with Easily-available Human Motions Estimated from Videoscited by 0
  7. 2025AugLift: Depth-Aware Input Reparameterization Improves Domain Generalization in 2D-to-3D Pose Liftingcited by 0
  8. 2025UniPose: Unified Cross-modality Pose Prior Propagation towards RGB-D data for Weakly Supervised 3D Human Pose Estimationcited by 0
  9. 2025PoseMoE: Mixture-of-Experts Network for Monocular 3D Human Pose Estimationcited by 0
  10. 2026Garment Inertial Denoiser (GID): Endowing Accurate Motion Capture via Loose IMU Denoisercited by 0
  11. 2026GazeD: Context-Aware Diffusion for Accurate 3D Gaze Estimationcited by 0