Research map / 3D vision / Human pose estimation
Probabilistic Inertial Poser (ProbIP): Uncertainty-aware Human Motion Modeling from Sparse Inertial Sensors
Min Kim, Younho Jeon, Sungho Jo
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 probabilistic matrix Fisher modeling (ablation) | ProbIP · DIP-IMU test | SIP error: 14.38 -> 13.65 | Improved |
| add probabilistic matrix Fisher modeling (ablation) | ProbIP · DIP-IMU test | Mesh error: 7.74 -> 5.61 | Improved |
| add Progressive Distribution Narrowing (ablation) | ProbIP · DIP-IMU test | SIP error: 15.55 -> 13.65 | Improved |
| add Progressive Distribution Narrowing (ablation) | ProbIP · DIP-IMU test | Angular error: 7.16 -> 6.57 | Improved |
| add rotation and uncertainty separation (RU-Mamba) (ablation) | ProbIP · DIP-IMU test | SIP error: 14.63 -> 13.65 | Improved |
| add rotation and uncertainty separation (RU-Mamba) (ablation) | ProbIP · DIP-IMU test | Mesh error: 5.72 -> 5.61 | Improved |
| w/o PDN position error lower than w/o prob but PDN still adds value (ablation) | ProbIP · DIP-IMU test | Position error: 5.07 -> 4.77 | Improved |
| add pelvis sensor (5 to 6 sensors) | ProbIP · DIP-IMU test | Angular error: 7.01 -> 6.57 | Improved |
| remove head sensor (5 to 4 sensors) | ProbIP · DIP-IMU test | Angular error: 7.01 -> 8.18 | Hurt |
| use ProbIP instead of DynaIP with 2 sensors | ProbIP · DIP-IMU test (2 sensors) | Angular error: 18.72 -> 12.49 | Improved |
| use ProbIP instead of DynaIP with 3 sensors | ProbIP · DIP-IMU test (3 sensors) | Angular error: 16.92 -> 10.71 | Improved |
| use ProbIP instead of DynaIP with 4 sensors | ProbIP · DIP-IMU test (4 sensors) | Angular error: 9.98 -> 8.18 | Improved |
Closest papers by meaning
- Dynamic Inertial Poser (DynaIP): Part-Based Motion Dynamics Learning for Enhanced Human Pose Estimation with Sparse Inertial Sensors (CVPR 2024 · similarity 0.88)
- UMotion: Uncertainty-driven Human Motion Estimation from Inertial and Ultra-wideband Units (CVPR 2025 · similarity 0.87)
- DiffusionPoser: Real-time Human Motion Reconstruction From Arbitrary Sparse Sensors Using Autoregressive Diffusion (CVPR 2024 · similarity 0.86)
- MODA: Motion-Drift Augmentation for Inertial Human Motion Analysis (CVPR 2025 · similarity 0.85)
- Loose Inertial Poser: Motion Capture with IMU-attached Loose-Wear Jacket (CVPR 2024 · similarity 0.84)
- Spatial-Related Sensors Matters: 3D Human Motion Reconstruction Assisted with Textual Semantics (AAAI 2024 · similarity 0.84)
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.
