Research map / 3D vision / Face and shape
Elastic Shape-From-Template With Spatially Sparse Deforming Forces
Abed Malti, Cedric Herzet
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 SLE instead of KFM | Elastic SfT · Silicone-lid | mean 3D reconstruction error (mm): 2.0[3.5] -> 1.2[1.7] | Improved |
| Use SLE instead of LM | Elastic SfT · Silicone-lid | mean 3D reconstruction error (mm): 1.9[2.7] -> 1.2[1.7] | Improved |
| Use SLE instead of KFM | Elastic SfT · Strip | mean 3D reconstruction error (mm): 2.1[2.5] -> 1.5[2.0] | Improved |
| Use SLE instead of LM | Elastic SfT · Strip | mean 3D reconstruction error (mm): 2.0[2.6] -> 1.5[2.0] | Improved |
| Use SLE instead of KFM | Elastic SfT · Clothes | mean 3D reconstruction error (mm): 2.9[3.5] -> 1.6[2.1] | Improved |
| Use SLE instead of AG | Elastic SfT · Clothes | mean 3D reconstruction error (mm): 2.8[2.2] -> 1.6[2.1] | Improved |
| Use SLE instead of KFM | Elastic SfT · Balloon | mean 3D reconstruction error (mm): 3.1[3.9] -> 1.6[1.9] | Improved |
| Use SLE instead of AG | Elastic SfT · Balloon | mean 3D reconstruction error (mm): 3.1[2.6] -> 1.6[1.9] | Improved |
| Use sparse force recovery rather than the compared force-agnostic or ℓ2-based approaches | Synthetic elastic SfT · Synthetic data | correct recovery of force support: exact location when sparsity goes to 45% of the total size of the vector (135 among 300 components) | Improved |
Closest papers by meaning
- f-SfT: Shape-From-Template With a Physics-Based Deformation Model (CVPR 2022 · similarity 0.90)
- Template-Based Monocular 3D Recovery of Elastic Shapes Using Lagrangian Multipliers (CVPR 2017 · similarity 0.88)
- A Stable Analytical Framework for Isometric Shape-from-Template by Surface Integration (TPAMI 2016 · similarity 0.87)
- Force-Based Representation for Non-Rigid Shape and Elastic Model Estimation (TPAMI 2017 · similarity 0.87)
- Image-Guided Shape-from-Template Using Mesh Inextensibility Constraints (ICCV 2025 · similarity 0.87)
- Physics-guided Shape-from-Template: Monocular Video Perception through Neural Surrogate Models (CVPR 2024 · similarity 0.83)
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.
