MPI-INF-3DHP

Overview edit

Variants: MPI-INF-3DHP

Associated Benchmarks

This dataset is used in 2 benchmarks:

• 3D Human Pose Estimation - Metrics: MPJPE, AUC, PCK, 3DPCK, PA-MPJPE, Acceleration Error
• Pose Retrieval - Metrics: Hit@1, Hit@10

Recent Benchmark Submissions

Research Papers

Recent papers with results on this dataset:

• TCPFormer: Learning Temporal Correlation with Implicit Pose Proxy for 3D Human Pose Estimation (2025) -
• ARTS: Semi-Analytical Regressor using Disentangled Skeletal Representations for Human Mesh Recovery from Videos (2024) -
• KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimation (2024) -
• Temporal-Aware Refinement for Video-based Human Pose and Shape Recovery (2023) -
• MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network (2023) -
• Refined Temporal Pyramidal Compression-and-Amplification Transformer for 3D Human Pose Estimation (2023) -
• Double-chain Constraints for 3D Human Pose Estimation in Images and Videos (2023) -
• GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Video (2023) -
• Back to Optimization: Diffusion-based Zero-Shot 3D Human Pose Estimation (2023) -
• XFormer: Fast and Accurate Monocular 3D Body Capture (2023) -
• Regular Splitting Graph Network for 3D Human Pose Estimation (2023) -
• TAPE: Temporal Attention-based Probabilistic human pose and shape Estimation (2023) -
• HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recovery (2023) -
• ConvFormer: Parameter Reduction in Transformer Models for 3D Human Pose Estimation by Leveraging Dynamic Multi-Headed Convolutional Attention (2023) -
• PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation (2023) -
• Global Adaptation meets Local Generalization: Unsupervised Domain Adaptation for 3D Human Pose Estimation (2023) -
• Global-to-Local Modeling for Video-based 3D Human Pose and Shape Estimation (2023) -
• DiffMesh: A Motion-aware Diffusion Framework for Human Mesh Recovery from Videos (2023) -
• Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation (2023) -
• HTNet: Human Topology Aware Network for 3D Human Pose Estimation (2023) -