mlsanityData to 14 Oct 2026

PoseBench3D: A Cross-Dataset Analysis Framework for 3D Human Pose Estimation via Pose Lifting Networks

arXiv 2505.10888 ↗First posted 16 May 2025cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Reliable three-dimensional human pose estimation (3D HPE) remains challenging due to the differences in viewpoints, environments, and camera conventions among datasets. As a result, methods that achieve near-optimal in-dataset accuracy often degrade on unseen datasets. In practice, however, systems must adapt to diverse viewpoints, environments, and camera setups--conditions that differ significantly from those encountered during training, which is often the case in real-world scenarios. Measuring cross-dataset performance is a vital process, but extremely labor-intensive when done manually for human pose estimation. To address these challenges, we automate this evaluation using PoseBench3D, a standardized testing framework that enables consistent and fair cross-dataset comparisons on previously unseen data. PoseBench3D streamlines testing across four widely used 3D HPE datasets via a single, configurable interface. Using this framework, we re-evaluate 18 methods and report over 100 cross-dataset results under Protocol 1: MPJPE and Protocol 2: PA-MPJPE, revealing systematic generalization gaps and the impact of common preprocessing and dataset setup choices. The PoseBench3D code is found at: https://github.com/bryanjvela/PoseBench3D

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 27 of its 51 references that are in the map. First posted on arXiv 16 May 2025.

Builds on

27 of 51 references.

References · 27

  1. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 403
  2. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  3. 2017Learning from Synthetic Humanscited by 359
  4. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 272
  5. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  6. 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 193
  7. 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 159
  8. 2021MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimationcited by 151
  9. 20163D Human Pose Estimation = 2D Pose Estimation + Matchingcited by 113
  10. 2021UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehiclescited by 96
  11. 2019Unsupervised 3D Pose Estimation with Geometric Self-Supervisioncited by 95
  12. 2020SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approachcited by 94
15 more
  1. 2019Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Networkcited by 92
  2. 2023PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimationcited by 92
  3. 2021PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimationcited by 89
  4. 2020Motion Guided 3D Pose Estimation from Videoscited by 85
  5. 2023Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregationcited by 82
  6. 2023MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Networkcited by 64
  7. 2021Conditional Directed Graph Convolution for 3D Human Pose Estimationcited by 52
  8. 2023GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Videocited by 47
  9. 2020Predicting Camera Viewpoint Improves Cross-dataset Generalization for 3D Human Pose Estimationcited by 36
  10. 2023DiffPose: SpatioTemporal Diffusion Model for Video-Based Human Pose Estimationcited by 36
  11. 2024KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimationcited by 34
  12. 2021AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generationcited by 32
  13. 2024FinePOSE: Fine-Grained Prompt-Driven 3D Human Pose Estimation via Diffusion Modelscited by 23
  14. 2025TCPFormer: Learning Temporal Correlation with Implicit Pose Proxy for 3D Human Pose Estimationcited by 14
  15. 2024Disentangled Diffusion-Based 3D Human Pose Estimation with Hierarchical Spatial and Temporal Denoisercited by 13

Built on by

Cited by year (2026 to 14 Oct)

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

2 papers.

  1. 2025AugLift: Depth-Aware Input Reparameterization Improves Domain Generalization in 2D-to-3D Pose Liftingcited by 1
  2. 2026UnrealPose: Leveraging Game Engine Kinematics for Large-Scale Synthetic Human Pose Datacited by 0