Research map / 3D vision / Face and shape
Local Deep Implicit Functions for 3D Shape
Check 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 |
|---|---|---|---|
| replace a single global implicit code with structured local deep implicit functions | 3D shape autoencoding · ShapeNet 3D-R²N² test set | F-Score: 10.3 points higher than OccNet | Helped |
| replace a single global implicit code with structured local deep implicit functions | 3D shape autoencoding · ShapeNet unseen classes | F-Score: 17.8 points higher than OccNet | Helped |
| use structured local deep implicit functions | single-depth-image completion · ShapeNet single-depth completion | F-Score: 15.8 points higher than OccNet* (78.2 vs. 62.4) | Helped |
| use LDIF rather than SIF | human body autoencoding · SMPL human body test set | mIOU: 93% mIOU compared to 85% mIOU | Helped |
| add local PointNet encoding for each shape element (ablation) | LDIF depth completion · ShapeNet depth completion ablation | F-Score: 66.2 -> 77.6 | Helped |
| transform query points into the local shape-element frame (ablation) | LDIF depth completion · ShapeNet depth completion ablation | F-Score: 71.9 -> 77.6 | Helped |
| add partial symmetry (ablation) | LDIF depth completion · ShapeNet depth completion ablation | F-Score: 76.6 -> 77.6 | Helped |
| add local PointNet encoding for each shape element (ablation) | LDIF depth completion · ShapeNet depth completion ablation | IoU: 69.1 -> 77.2 | Helped |
| transform query points into the local shape-element frame (ablation) | LDIF depth completion · ShapeNet depth completion ablation | Chamfer distance: 1.80 -> 0.78 | Helped |
| remove partial symmetry (ablation) | LDIF depth completion · ShapeNet depth completion ablation | Chamfer distance: 0.76 vs. 0.78 | No clear effect |
Closest papers by meaning
- LP-DIF: Learning Local Pattern-Specific Deep Implicit Function for 3D Objects and Scenes (CVPR 2023 · similarity 0.93)
- DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation (CVPR 2019 · similarity 0.91)
- A Lightweight UDF Learning Framework for 3D Reconstruction Based on Local Shape Functions (CVPR 2025 · similarity 0.90)
- LISR: Learning Linear 3D Implicit Surface Representation Using Compactly Supported Radial Basis Functions (AAAI 2024 · similarity 0.89)
- Few-Shot Unsupervised Implicit Neural Shape Representation Learning with Spatial Adversaries (ICML 2024 · similarity 0.88)
- Implicit Modeling of Non-rigid Objects with Cross-Category Signals (AAAI 2024 · similarity 0.88)
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.