Research map / 3D vision / Face and shape
OReX: Object Reconstruction From Planar Cross-Sections Using Neural Fields
Haim Sawdayee, Amir Vaxman, Amit H. Bermano
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 OReX instead of the strongest listed baseline | Planar cross-section reconstruction · Eight (S) | Hausdorff distance: 0.046 -> 0.018 | Improved |
| Use OReX instead of the strongest listed baseline | Planar cross-section reconstruction · Eight (S) | IoU in 3d: 0.961 -> 0.984 | Improved |
| Use OReX instead of the strongest listed baseline | Planar cross-section reconstruction · Elephant | Hausdorff distance: 0.081 -> 0.056 | Improved |
| Use OReX instead of the strongest listed baseline | Planar cross-section reconstruction · Elephant | IoU in 3d: 0.935 -> 0.966 | Improved |
| Use OReX instead of the strongest listed baseline | Planar cross-section reconstruction · Balloon dog | Hausdorff distance: 0.078 -> 0.049 | Improved |
| Use OReX instead of the strongest listed baseline | Planar cross-section reconstruction · Hand OK | IoU in 2d: 0.968 -> 0.987 | Improved |
| Add hinge-loss gradient regularization near input boundaries (ablation) | OReX · Mesh extraction from planar cross-sections | ripple artifacts | Improved |
| Increase the number of refinement iterations (ablation) | OReXNet · Planar cross-section reconstruction | high-frequency detail representation | Improved |
| Use hierarchical frequency-oriented boundary sampling instead of non-hierarchical distance sampling (ablation) | OReX · Planar cross-section reconstruction | detail quality | Improved |
| Use gradually increasing sampling resolution rather than a single grid resolution (ablation) | OReX · Planar cross-section reconstruction | high-frequency detail representation | Improved |
| Replace hierarchical importance sampling and iterative refinement with uniform grid sampling and no refinement (ablation) | OReX · Planar cross-section reconstruction | detail preservation | Hurt |
Closest papers by meaning
- Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction (ICLR 2023 · similarity 0.88)
- Front2Back: Single View 3D Shape Reconstruction via Front to Back Prediction (CVPR 2020 · similarity 0.87)
- Neural Fields As Learnable Kernels for 3D Reconstruction (CVPR 2022 · similarity 0.87)
- UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflections (NeurIPS 2024 · similarity 0.86)
- Object-X: Learning to Reconstruct Multi-Modal 3D Object Representations (NeurIPS 2025 · similarity 0.86)
- CrossSDF: 3D Reconstruction of Thin Structures From Cross-Sections (CVPR 2025 · 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.
