Research map / 3D vision / Face and shape
Learning to Infer Implicit Surfaces without 3D Supervision
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 the implicit-surface framework instead of the strongest listed explicit-representation baseline | single-view ShapeNet reconstruction · ShapeNet mean | 3D IoU: 0.5850 -> 0.6067 | Helped |
| use the implicit-surface framework instead of SoftRas | single-view ShapeNet reconstruction · ShapeNet Boat | 3D IoU: 0.6145 -> 0.6080 | Hurt |
| add geometric regularization with norm p=0.8 rather than removing the regularizer (ablation) | implicit-surface model · ShapeNet Chair | 3D IoU: 0.503 -> 0.548 | Helped |
| set the geometric regularizer norm to p=0.8 rather than p=1.0 (ablation) | implicit-surface model · ShapeNet Chair | 3D IoU: 0.524 -> 0.548 | Helped |
| set the geometric regularizer norm to p=0.8 rather than p=2.0 (ablation) | implicit-surface model · ShapeNet Chair | 3D IoU: 0.502 -> 0.548 | Helped |
| set regularizer sampling step Δd=3×10⁻² rather than 1×10⁻² (ablation) | implicit-surface model · ShapeNet Table | 3D IoU: 0.482 -> 0.515 | Helped |
| set regularizer sampling step Δd=3×10⁻² rather than 1×10⁻¹ (ablation) | implicit-surface model · ShapeNet Table | 3D IoU: 0.507 -> 0.515 | Helped |
| use importance sampling rather than normal sampling for anchor points and rays (ablation) | implicit-surface model · ShapeNet Chair | 3D IoU: 0.482 -> 0.548 | Helped |
| add boundary-aware assignment (ablation) | implicit-surface model · ShapeNet Chair | 3D IoU: 0.524 -> 0.548 | Helped |
Closest papers by meaning
- OctField: Hierarchical Implicit Functions for 3D Modeling (NeurIPS 2021 · similarity 0.90)
- Local Deep Implicit Functions for 3D Shape (CVPR 2020 · similarity 0.90)
- Iso-Points: Optimizing Neural Implicit Surfaces With Hybrid Representations (CVPR 2021 · similarity 0.90)
- NeAT: Learning Neural Implicit Surfaces With Arbitrary Topologies From Multi-View Images (CVPR 2023 · similarity 0.90)
- LISR: Learning Linear 3D Implicit Surface Representation Using Compactly Supported Radial Basis Functions (AAAI 2024 · similarity 0.89)
- 4Deform: Neural Surface Deformation for Robust Shape Interpolation (CVPR 2025 · 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.