Research map / 3D vision / Human pose estimation
Kinematic-Structure-Preserved Representation for Unsupervised 3D Human Pose Estimation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use the kinematic-structure-preserved framework without pose supervision | Ours (unsup.) · Human3.6M protocol-II | MPJPE (Avg.): 98.2 -> 89.4 | Helped |
| Use full 2D pose supervision | Ours (unsup.) · Human3.6M protocol-II | MPJPE (Avg.): 89.4 -> 63.8 | Helped |
| Use 5%-3D supervision | Ours (unsup.) · Human3.6M protocol-II | MPJPE (Avg.): 89.4 -> 56.1 | Helped |
| Use full 2D pose supervision | Ours (unsup.) · MPI-INF-3DHP | PCK: 79.2 -> 80.2 | Helped |
| Use full 2D pose supervision | Ours (unsup.) · MPI-INF-3DHP | AUC: 43.4 -> 44.8 | Helped |
| Use full 2D pose supervision | Ours (unsup.) · MPI-INF-3DHP | MPJPE: 99.2 -> 97.1 | Helped |
| Add the forward-kinematic transformation (ablation) | Ours (unsup.) · MPI-INF-3DHP test set | 3DPCK: 47.9 -> 71.2 | Helped |
| Add the forward-kinematic transformation (ablation) | Ours (unsup.) · Human3.6M | MPJPE: 134.8 -> 89.4 | Helped |
| Add the spatial-map transformation (ablation) | Ours (unsup.) · MPI-INF-3DHP test set | 3DPCK: 61.7 -> 71.2 | Helped |
| Add the spatial-map transformation (ablation) | Ours (unsup.) · Human3.6M | MPJPE: 101.8 -> 89.4 | Helped |
| Train with unpaired video samples using the energy-based loss (ablation) | Ours (unsup.) · MPI-INF-3DHP test set | 3DPCK: 66.3 -> 71.2 | Helped |
| Train with unpaired video samples using the energy-based loss (ablation) | Ours (unsup.) · Human3.6M | MPJPE: 91.1 -> 89.4 | Helped |
Closest papers by meaning
- Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesis (CVPR 2020 · similarity 0.92)
- Weakly-Supervised Discovery of Geometry-Aware Representation for 3D Human Pose Estimation (CVPR 2019 · similarity 0.92)
- 3D Human Pose Estimation From a Single Image via Distance Matrix Regression (CVPR 2017 · similarity 0.91)
- Weakly-Supervised 3D Human Pose Learning via Multi-View Images in the Wild (CVPR 2020 · similarity 0.91)
- Unsupervised 3D Pose Estimation With Geometric Self-Supervision (CVPR 2019 · similarity 0.90)
- Capturing the Motion of Every Joint: 3D Human Pose and Shape Estimation with Independent Tokens (ICLR 2023 · similarity 0.90)
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.