Research map / 3D vision / Human pose estimation
Force-Based Representation for Non-Rigid Shape and Elastic Model Estimation
Antonio Agudo, Francesc Moreno-Noguer
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 |
|---|---|---|---|
| estimate the full compliance matrix C instead of fixing C = I (ablation) | EM-PFS · Mocap average, noise-free | e3D error (%): 5.14 -> 4.62 | Improved |
| estimate the full compliance matrix C instead of fixing C = I (ablation) | EM-PFS · Mocap average, noisy observations | e3D error (%): 6.57 -> 5.58 | Improved |
| estimate compliance matrix C instead of C = I on Face sequence (ablation) | EM-PFS · Face noise-free | e3D error (%): 3.86 -> 2.85 | Improved |
| force-space model versus shape-space EM-PPCA (ablation) | EM-PFS · Mocap average, noise-free | e3D error (%): 6.11 -> 4.62 | Improved |
| force-space model versus SPM (ablation) | EM-PFS · Mocap average, noise-free | e3D error (%): 5.09 -> 4.62 | Improved |
| force-space model versus KSTA under noise (ablation) | EM-PFS · Mocap average, noisy observations | e3D error (%): 7.45 -> 5.58 | Improved |
| use inextensibility constraint IFM instead of force model under noise (ablation) | IFM · Mocap average, noisy observations | e3D error (%): 5.58 -> 12.91 | Hurt |
| increase force subspace rank Q (ablation) | EM-PFS · Jacky and Flag Mocap | e3D error (%) | No clear effect |
| increase force subspace rank Q (ablation) | EM-PFS · Face and Walking Mocap | e3D error (%) | Mixed |
| use rigid boundary conditions (B=14 points) on face contour (ablation) | EM-PFS · ASL1 computation time | seconds: 588 -> 374 | Improved |
| use rigid boundary conditions (B=14 points) on face contour (ablation) | EM-PFS · ASL2 computation time | seconds: 583 -> 369 | Improved |
| use boundary conditions on reconstruction quality (ablation) | EM-PFS · ASL sequences | visual quality | No clear effect |
Closest papers by meaning
- Template-Based Monocular 3D Recovery of Elastic Shapes Using Lagrangian Multipliers (CVPR 2017 · similarity 0.88)
- MORPH-DSLAM: Model Order Reduction for Physics-Based Deformable SLAM (TPAMI 2021 · similarity 0.87)
- Learning Implicit Representation for Reconstructing Articulated Objects (ICLR 2024 · similarity 0.86)
- REACTO: Reconstructing Articulated Objects from a Single Video (CVPR 2024 · similarity 0.86)
- Hand-held Object Reconstruction from RGB Video with Dynamic Interaction (CVPR 2025 · similarity 0.86)
- Neural Parametric Gaussians for Monocular Non-Rigid Object Reconstruction (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.
