Research map / 3D vision / Face and shape
Octree Guided Unoriented Surface Reconstruction
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Guide SIREN training with labelled octree supervision | SIREN without normals · ShapeNet | IoU (mean): 0.3085 -> 0.9615 | Helped |
| Guide SIREN training with labelled octree supervision | SIREN without normals · ShapeNet | squared Chamfer distance (mean): 3.08e-4 -> 3.75e-5 | Helped |
| Guide SIREN training with labelled octree supervision | SIREN without normals · SRB | Chamfer distance: 0.42 -> 0.20 | Helped |
| Guide SIREN training with labelled octree supervision | SIREN without normals · SRB | Hausdorff distance: 7.67 -> 4.06 | Helped |
| Increase octree depth from 5 to 7 (ablation) | OG-SIREN · ShapeNet | IoU (mean): 0.7101 -> 0.9615 | Helped |
| Increase octree depth from 5 to 7 (ablation) | OG-SIREN · ShapeNet | squared Chamfer distance (mean): 1.84e-4 -> 3.75e-5 | Helped |
| Add sparse human occupancy labels to octree leaves (ablation) | OG-SIREN · SRB | Hausdorff distance: 4.06 -> 2.96 | Helped |
| Add ground-truth occupancy labels to octree leaves (ablation) | OG-SIREN · SRB | Hausdorff distance: 4.06 -> 2.44 | Helped |
| Add sparse human occupancy labels to octree leaves (ablation) | OG-NGLOD · SRB | Hausdorff distance: 6.03 -> 5.50 | Helped |
| Add ground-truth occupancy labels to octree leaves (ablation) | OG-NGLOD · SRB | Hausdorff distance: 6.03 -> 5.12 | Helped |
Closest papers by meaning
- OctField: Hierarchical Implicit Functions for 3D Modeling (NeurIPS 2021 · similarity 0.89)
- DiGS: Divergence Guided Shape Implicit Neural Representation for Unoriented Point Clouds (CVPR 2022 · similarity 0.89)
- OffsetOPT: Explicit Surface Reconstruction without Normals (CVPR 2025 · similarity 0.87)
- Occlusion-aware Non-Rigid Point Cloud Registration via Unsupervised Neural Deformation Correntropy (ICLR 2025 · similarity 0.86)
- Flatten Anything: Unsupervised Neural Surface Parameterization (NeurIPS 2024 · similarity 0.86)
- Small Steps and Level Sets: Fitting Neural Surface Models with Point Guidance (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.