Research map / 3D vision / Face and shape
Template-Based Monocular 3D Shape Recovery Using Laplacian Meshes
Dat Tien Ngo, Jonas Östlund, Pascal Fua
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 |
|---|---|---|---|
| use regularly sampled control vertices instead of random control vertices (ablation) | Laplacian mesh reconstruction · Kinect and sail sequences | reconstruction error | No clear effect |
| reduce dimensionality by expressing vertices as linear combinations of control vertices (vs all vertices) (ablation) | Laplacian mesh reconstruction · Paper, apron, cushion, leaf, sail | reconstruction accuracy | No clear effect |
| use too few control vertices (ablation) | Laplacian mesh reconstruction · Planar and non-planar templates | reconstruction accuracy | No clear effect |
| use our Laplacian method instead of Bartoli et al. on the apron sequence | planar template reconstruction · Apron | reconstruction accuracy | Improved |
| use our method instead of the others on non-planar cushion and leaf | non-planar template reconstruction · Cushion, banana leaf | reconstruction accuracy | Improved |
| use our outlier rejection instead of Bartoli et al. | outlier rejection · Paper dataset (~600000 correspondences) | time per frame: 1.18 -> 0.070 seconds per frame | Improved |
| use our outlier rejection instead of Brunet et al. | outlier rejection · Cushion dataset (~600000 correspondences) | time per frame: 0.29 -> 0.089 seconds per frame | Improved |
| use regularization weight within 1 to 10 (ablation) | Laplacian mesh reconstruction · Kinect sequences | mean reconstruction error | No clear effect |
Closest papers by meaning
- Template-Based Monocular 3D Recovery of Elastic Shapes Using Lagrangian Multipliers (CVPR 2017 · similarity 0.88)
- In Perfect Shape: Certifiably Optimal 3D Shape Reconstruction From 2D Landmarks (CVPR 2020 · similarity 0.87)
- A Stable Analytical Framework for Isometric Shape-from-Template by Surface Integration (TPAMI 2016 · similarity 0.87)
- SobolevFusion: 3D Reconstruction of Scenes Undergoing Free Non-Rigid Motion (CVPR 2018 · similarity 0.86)
- Learning Delaunay Surface Elements for Mesh Reconstruction (CVPR 2021 · similarity 0.86)
- SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images (CVPR 2025 · 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.
