Research map / 3D vision / Face and shape
OctField: Hierarchical Implicit Functions for 3D Modeling
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 |
|---|---|---|---|
| Use adaptive octree subdivision with local implicit functions instead of regular-grid local implicit functions | OctField · ShapeNet mean | CD (×10^-4): 3.27 -> 2.97 | Helped |
| Use adaptive octree subdivision with local implicit functions instead of regular-grid local implicit functions | OctField · ShapeNet mean | EMD (×10^-2): 2.63 -> 2.19 | Helped |
| Use adaptive octree subdivision with local implicit functions instead of regular-grid local implicit functions | OctField · ShapeNet reconstruction | mIoU: 86.28 -> 87.96 | Helped |
| Use adaptive octree subdivision with local implicit functions instead of regular-grid local implicit functions | OctField · ShapeNet reconstruction | F1: 0.93 -> 0.94 | Helped |
| Use adaptive octree subdivision with local implicit functions | OctField · 3D-Front | CD (×10^-4): 7.1 -> 6.4 | Helped |
| Use adaptive octree subdivision with local implicit functions | OctField · 3D-Front | EMD (×10^-2): 22.3 -> 21.1 | Helped |
| Use OctField's hierarchical representation for completion from partial point clouds | OctField · ShapeNet table completion | CD (×10^-4): 4.9 -> 4.4 | Helped |
| Use adaptive subdivision rather than regular decomposition | OctField · Decomposition level 4 | local implicit cell count: 4096 -> 1000 | Helped |
| Use adaptive subdivision rather than regular decomposition | OctField · Decomposition level 4 | memory (GB): 40 -> 23 | Helped |
Closest papers by meaning
- Learning to Infer Implicit Surfaces without 3D Supervision (NeurIPS 2019 · similarity 0.90)
- Neural Geometric Level of Detail: Real-Time Rendering With Implicit 3D Shapes (CVPR 2021 · similarity 0.90)
- Octree Guided Unoriented Surface Reconstruction (CVPR 2023 · similarity 0.89)
- Local Implicit Grid Representations for 3D Scenes (CVPR 2020 · similarity 0.89)
- GALA: Geometry-Aware Local Adaptive Grids for Detailed 3D Generation (ICLR 2025 · similarity 0.87)
- Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapes (CVPR 2024 · similarity 0.87)
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.