Research map / 3D vision / Face and shape
In Perfect Shape: Certifiably Optimal 3D Shape Reconstruction From 2D Landmarks
Heng Yang, Luca Carlone
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 order-2 SOS relaxation for joint shape and camera-pose reconstruction | Shape★ · Outlier-free simulated shape reconstruction | 3D shape and rotation estimation error | Improved |
| Use truncated least squares with graduated non-convexity for outlier rejection | ShapeRobust · FG3DCar | outlier tolerance: 70% | Improved |
| Replace the full monomial basis with the reduced monomial basis (ablation) | Shape★ · Simulation, K=20 | SDP time [s]: 2440 -> 107 | Improved |
| Replace the full monomial basis with the reduced monomial basis (ablation) | Shape★ · Simulation, K=5, K=10, K=20 | coefficient estimation error: 1.3e-3 -> 1.3e-3; 2.3e-3 -> 2.3e-3; 3.2e-3 -> 3.2e-3 | No clear effect |
| Replace the full monomial basis with the reduced monomial basis (ablation) | Shape★ · Simulation, K=5, K=10, K=20 | rotation estimation error [deg]: 0.0690 -> 0.0690; 0.0487 -> 0.0487; 0.0298 -> 0.0298 | No clear effect |
| Use ShapeRobust rather than robustified alternative optimization or robustified convex optimization | FG3DCar reconstruction · FG3DCar, increasing outlier rates | shape and rotation estimation error: 70% | Improved |
Closest papers by meaning
- Sparse Representation for 3D Shape Estimation: A Convex Relaxation Approach (TPAMI 2016 · similarity 0.93)
- A Simple, Fast and Highly-Accurate Algorithm to Recover 3D Shape from 2D Landmarks on a Single Image (TPAMI 2017 · similarity 0.88)
- Certifiably Optimal Outlier-Robust Geometric Perception: Semidefinite Relaxations and Scalable Global Optimization (TPAMI 2022 · similarity 0.88)
- Template-Based Monocular 3D Shape Recovery Using Laplacian Meshes (TPAMI 2016 · similarity 0.87)
- Robust 3D Shape Reconstruction in Zero-Shot from a Single Image in the Wild (CVPR 2025 · similarity 0.87)
- FSC: Few-point Shape Completion (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.
