Research map / 3D vision / Human pose estimation
PersPose: 3D Human Pose Estimation with Perspective Encoding and Perspective Rotation
Xiaoyang Hao, Han Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add perspective encoding (PE) (ablation) | PersPose · 3DPW (train R) | MPJPE: 62.4 -> 62.2 | Improved |
| add perspective encoding (PE) (ablation) | PersPose · MPI-INF-3DHP (train R) | MPJPE: 80.1 -> 76.6 | Improved |
| add perspective rotation (PR) on top of PE (ablation) | PersPose · 3DPW (train R) | MPJPE: 62.2 -> 60.1 | Improved |
| add perspective rotation (PR) on top of PE (ablation) | PersPose · MPI-INF-3DHP (train R) | MPJPE: 76.6 -> 71.9 | Improved |
| add perspective rotation (PR) on top of PE (ablation) | PersPose · 3DPW (train R+B) | MPJPE: 58.1 -> 57.2 | Improved |
| add perspective rotation (PR) on top of PE (ablation) | PersPose · MPI-INF-3DHP (train R+B) | MPJPE: 73.4 -> 70.2 | Improved |
| add PE and PR (ablation) | PersPose · 3DPW (train R) | depth error: 45.1 -> 43.8 | Improved |
| add PE and PR (ablation) | PersPose · MPI-INF-3DHP (train R) | depth error: 57.3 -> 51.0 | Improved |
| add PE and PR (ablation) | PersPose · 3DPW (train R+B) | PA-MPJPE: 37.8 -> 37.3 | Improved |
| add BEDLAM synthetic data to training (ablation) | PersPose · 3DPW | MPJPE: 60.1 -> 57.2 | Improved |
| add BEDLAM synthetic data to training (ablation) | PersPose · MPI-INF-3DHP | MPJPE: 71.9 -> 70.2 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- PLIKS — PLIKS: A Pseudo-Linear Inverse Kinematic Solver for 3D Human Body Estimation (CVPR 2023) · better on 4 of 4 shared results
- ProPose — ProPose: Probabilistic 3D Human Pose Estimation with Instance-Level Distribution and Normalizing Flow (AAAI 2025) · better on 2 of 2 shared results
- CLIFF — CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation (ECCV 2022) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos (CVPR 2025 · similarity 0.87)
- SVTformer: Spatial-View-Temporal Transformer for Multi-View 3D Human Pose Estimation (AAAI 2025 · similarity 0.87)
- $\text{Di}^2\text{Pose}$: Discrete Diffusion Model for Occluded 3D Human Pose Estimation (NeurIPS 2024 · similarity 0.86)
- SHaRPose: Sparse High-Resolution Representation for Human Pose Estimation (AAAI 2024 · similarity 0.86)
- MV-SSM: Multi-View State Space Modeling for 3D Human Pose Estimation (CVPR 2025 · similarity 0.86)
- FreeMan: Towards Benchmarking 3D Human Pose Estimation under Real-World Conditions (CVPR 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
