mlsanityData to 14 Oct 2026

Improving the Robustness of 3D Human Pose Estimation: A Benchmark and Learning from Noisy Input

arXiv 2312.06797 ↗First posted 11 Dec 2023cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Despite the promising performance of current 3D human pose estimation techniques, understanding and enhancing their generalization on challenging in-the-wild videos remain an open problem. In this work, we focus on the robustness of 2D-to-3D pose lifters. To this end, we develop two benchmark datasets, namely Human3.6M-C and HumanEva-I-C, to examine the robustness of video-based 3D pose lifters to a wide range of common video corruptions including temporary occlusion, motion blur, and pixel-level noise. We observe the poor generalization of state-of-the-art 3D pose lifters in the presence of corruption and establish two techniques to tackle this issue. First, we introduce Temporal Additive Gaussian Noise (TAGN) as a simple yet effective 2D input pose data augmentation. Additionally, to incorporate the confidence scores output by the 2D pose detectors, we design a confidence-aware convolution (CA-Conv) block. Extensively tested on corrupted videos, the proposed strategies consistently boost the robustness of 3D pose lifters and serve as new baselines for future research.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 49 of its 64 references that are in the map. First posted on arXiv 11 Dec 2023.

Builds on

49 of 64 references.

References · 49

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  3. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  4. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,209
  5. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,162
  6. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 494
  7. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 403
  8. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  9. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  10. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 337
  11. 2019Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Comingcited by 336
  12. 2016Convolutional Pose Machinescited by 325
37 more
  1. 2021HuMoR: 3D Human Motion Model for Robust Pose Estimationcited by 324
  2. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 272
  3. 2017Integral Human Pose Regressioncited by 256
  4. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 221
  5. 2020Monocular, One-stage, Regression of Multiple 3D Peoplecited by 218
  6. 2021Putting People in their Place: Monocular Regression of 3D People in Depthcited by 142
  7. 2017VNect: Real-time 3D Human Pose Estimation with a Single RGB Cameracited by 129
  8. 2017Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approachcited by 115
  9. 20163D Human Pose Estimation = 2D Pose Estimation + Matchingcited by 113
  10. 2019Benchmarking the Robustness of Semantic Segmentation Modelscited by 111
  11. 20182D/3D Pose Estimation and Action Recognition using Multitask Deep Learningcited by 103
  12. 2020SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approachcited by 94
  13. 2021Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimationcited by 94
  14. 2021Lite-HRNet: A Lightweight High-Resolution Networkcited by 91
  15. 2021PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimationcited by 89
  16. 2020Motion Guided 3D Pose Estimation from Videoscited by 85
  17. 2020Cascaded deep monocular 3D human pose estimation with evolutionary training datacited by 80
  18. 2019Monocular 3D Human Pose Estimation by Generation and Ordinal Rankingcited by 76
  19. 20163D Human Pose Estimation from a Single Image via Distance Matrix Regressioncited by 73
  20. 2017Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Imagecited by 73
  21. 2021Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimationcited by 62
  22. 2022FLAG: Flow-based 3D Avatar Generation from Sparse Observationscited by 55
  23. 2015Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Videocited by 54
  24. 20203D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Trainingcited by 54
  25. 2021Conditional Directed Graph Convolution for 3D Human Pose Estimationcited by 52
  26. 20203D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Datacited by 50
  27. 2021When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarkscited by 41
  28. 2021ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Posescited by 35
  29. 2020Full-Body Awareness from Partial Observationscited by 29
  30. 20163D Human Pose Estimation Using Convolutional Neural Networks with 2D Pose Informationcited by 28
  31. 2015Direct Prediction of 3D Body Poses from Motion Compensated Sequencescited by 26
  32. 2021Skeletor: Skeletal Transformers for Robust Body-Pose Estimationcited by 26
  33. 2018How Robust is 3D Human Pose Estimation to Occlusion?cited by 23
  34. 2021Improving Robustness and Accuracy via Relative Information Encoding in 3D Human Pose Estimationcited by 18
  35. 2021Show or Suppress? Managing Input Uncertainty in Machine Learning Model Explanationscited by 15
  36. 2018Synthetic Occlusion Augmentation with Volumetric Heatmaps for the 2018 ECCV PoseTrack Challenge on 3D Human Pose Estimationcited by 8
  37. 2022Towards a Comprehensive Solution for a Vision-based Digitized Neurological Examinationcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 2.

4 papers.

  1. 2025Online Test-time Adaptation for 3D Human Pose Estimation: A Practical Perspective with Estimated 2D Posescited by 1
  2. 2026CIGPose: Causal Intervention Graph Neural Network for Whole-Body Pose Estimationcited by 1
  3. 2024R.I.P.: A Simple Black-box Attack on Continual Test-time Adaptationcited by 0
  4. 2026Pose-Aware Multimodal Automatic Tagging for Greek Traditional Musiccited by 0