Research map / 3D vision / 3D generation
Curve Reconstruction via the Global Statistics of Natural Curves
Ehud Barnea, Ohad Ben-Shahar
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 the global-statistics mean curve rather than Euler Spiral completion | Curve reconstruction · CFGD reconstruction benchmark | AUC: 0.876 -> 0.887 | Improved |
| Use the global-statistics mean curve rather than Euler Spiral completion | Curve reconstruction · CFGD difficult configurations | AUC: 0.492 -> 0.621 | Improved |
| Pool curve fragments across scales using mean-curve scale invariance (ablation) | Basic mean-curve reconstruction · Natural curve configurations, especially longer gaps | Reconstruction quality | Improved |
| Add midway extensibility by reconstructing two sub-curves through the center (ablation) | Scale-invariant mean-curve reconstruction · Low-sample configurations | Reconstruction quality | Improved |
| Assume scale invariance for difficult configurations where the evidence is inconclusive (ablation) | Scale-invariant mean-curve reconstruction · Abnormal inducer configurations | Reconstruction quality | No clear effect |
Closest papers by meaning
- From Multiview Image Curves to 3D Drawings (ECCV 2016 · similarity 0.85)
- Curve-Aware Gaussian Splatting for 3D Parametric Curve Reconstruction (ICCV 2025 · similarity 0.85)
- Front2Back: Single View 3D Shape Reconstruction via Front to Back Prediction (CVPR 2020 · similarity 0.85)
- Learning to Reconstruct Shapes from Unseen Classes (NeurIPS 2018 · similarity 0.85)
- Robust 3D Shape Reconstruction in Zero-Shot from a Single Image in the Wild (CVPR 2025 · similarity 0.84)
- Multistable Shape from Shading Emerges from Patch Diffusion (NeurIPS 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.
