Research map / 3D vision / Face and shape
Template-Based Monocular 3D Recovery of Elastic Shapes Using Lagrangian Multipliers
Nazim Haouchine, Stephane Cotin
Check 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 |
|---|---|---|---|
| Use the Lagrangian-multiplier formulation instead of force minimization (FM) | Elastic monocular 3D recovery · Silicone elastic data, Deformations 1–4 | Mean 3D error (mm): 1.99 -> 1.66; 2.00 -> 1.27; 1.56 -> 1.55; 1.19 -> 1.31 | Mixed |
| Use the Lagrangian-multiplier formulation instead of force minimization (FM) | Elastic monocular 3D recovery · Silicone elastic data, Deformations 1–4 | RMS 3D error (mm): 2.62 -> 1.93; 2.44 -> 1.60; 2.06 -> 1.91; 1.69 -> 1.51 | Improved |
| Add fixed boundary conditions (ablation) | LM elastic 3D recovery · Synthetic elastic data | 3D mean error (mm) | Improved |
| Add fixed boundary conditions (ablation) | FM elastic 3D recovery · Synthetic elastic data | 3D mean error (mm) | Improved |
| Vary Young's modulus across the tested range (ablation) | LM elastic 3D recovery · Synthetic elastic data | 3D mean error (mm) | No clear effect |
| Vary Poisson's ratio across the tested range (ablation) | LM elastic 3D recovery · Synthetic elastic data | 3D mean error (mm) | No clear effect |
| Reduce the number of image features and add Gaussian localization noise (ablation) | LM elastic 3D recovery · Synthetic elastic data | 3D mean error (mm) | No clear effect |
| Apply an inextensibility-based method instead of LM | Elastic monocular 3D recovery · Silicone elastic data, Deformation 4 | Mean 3D error (mm): 1.31 -> 4.87 | Hurt |
Closest papers by meaning
- Elastic Shape-From-Template With Spatially Sparse Deforming Forces (CVPR 2017 · similarity 0.88)
- Force-Based Representation for Non-Rigid Shape and Elastic Model Estimation (TPAMI 2017 · similarity 0.88)
- Template-Based Monocular 3D Shape Recovery Using Laplacian Meshes (TPAMI 2016 · similarity 0.88)
- Physics-guided Shape-from-Template: Monocular Video Perception through Neural Surrogate Models (CVPR 2024 · similarity 0.86)
- Physically Compatible 3D Object Modeling from a Single Image (NeurIPS 2024 · similarity 0.85)
- MonoPhysics: Estimating Geometry, Appearance, and Physical Parameters from Monocular Videos (NeurIPS 2026 · similarity 0.85)
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.
