Research map / Point clouds / Shape and surface completion
Implicit Geometric Regularization for Learning Shapes
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 implicit geometric regularization instead of DGP | Ours · Anchor ground truth | Chamfer distance: 0.33 -> 0.22 | Helped |
| Use implicit geometric regularization instead of DGP | Ours · Daratech ground truth | Chamfer distance: 0.2 -> 0.25 | Hurt |
| Use implicit geometric regularization instead of DGP | Ours · Dc ground truth | Chamfer distance: 0.18 -> 0.17 | Helped |
| Use implicit geometric regularization instead of DGP | Ours · Gargoyle ground truth | Chamfer distance: 0.21 -> 0.16 | Helped |
| Use implicit geometric regularization instead of DGP | Ours · Lord Quas ground truth | Chamfer distance: 0.14 -> 0.12 | Helped |
| Use implicit geometric regularization instead of DGP | Ours · Anchor ground truth | Hausdorff distance: 8.82 -> 4.71 | Helped |
| Use implicit geometric regularization instead of DGP | Ours · Daratech ground truth | Hausdorff distance: 3.14 -> 4.01 | Hurt |
| Use implicit geometric regularization instead of DGP | Ours · Dc ground truth | Hausdorff distance: 4.31 -> 2.22 | Helped |
| Use implicit geometric regularization instead of DGP | Ours · Gargoyle ground truth | Hausdorff distance: 5.98 -> 3.52 | Helped |
| Use implicit geometric regularization instead of DGP | Ours · Lord Quas ground truth | Hausdorff distance: 3.67 -> 1.17 | Helped |
| Fit the implicit surface to raw points with geometric regularization rather than nearby SDF regression | Ours · D-Faust human scans | Level of detail and fidelity | Helped |
| Train on raw scans with an auto-decoder shape space | Ours · D-Faust shape space | Reconstruction quality | Helped |
Closest papers by meaning
- Few-Shot Unsupervised Implicit Neural Shape Representation Learning with Spatial Adversaries (ICML 2024 · similarity 0.90)
- Iso-Points: Optimizing Neural Implicit Surfaces With Hybrid Representations (CVPR 2021 · similarity 0.90)
- DiGS: Divergence Guided Shape Implicit Neural Representation for Unoriented Point Clouds (CVPR 2022 · similarity 0.89)
- NeuralIndicator: Implicit Surface Reconstruction from Neural Indicator Priors (ICML 2024 · similarity 0.88)
- LISR: Learning Linear 3D Implicit Surface Representation Using Compactly Supported Radial Basis Functions (AAAI 2024 · similarity 0.88)
- Small Steps and Level Sets: Fitting Neural Surface Models with Point Guidance (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.