Research map / Point clouds / Segmentation and detection
A Minimalist Approach to Type-Agnostic Detection of Quadrics in Point Clouds
Tolga Birdal, Benjamin Busam, Nassir Navab, Slobodan Ilic, Peter Sturm
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 a 3-point basis with local null-space voting instead of the 4-point variant (ablation) | Generic quadric detector · Real scenes with clutter and occlusion | detection accuracy | No clear effect |
| Use a 3-point basis with local null-space voting instead of the 4-point variant (ablation) | Generic quadric detector · Real scenes with clutter and occlusion | runtime | Improved |
| Use the compact common-scale fit rather than the full fit with per-normal scales (ablation) | Quadric fitting · Synthetic quadrics at low noise | fit accuracy | Hurt |
| Use the compact common-scale fit rather than the full fit with per-normal scales (ablation) | Quadric fitting · Synthetic quadrics as noise increases | fit stability | Improved |
| Use a generic type-agnostic quadric detector rather than a cylinder-specific model detector | ITODD cylinders · ITODD cylinders | detection performance: 41.9% vs 72%, 73%, 74%, 24%, 86% | Mixed |
| Redesign the fitting matrix for a specific primitive type | Quadric detector · Type-specific detection | detection accuracy | Improved |
Closest papers by meaning
- Generic Primitive Detection in Point Clouds Using Novel Minimal Quadric Fits (TPAMI 2019 · similarity 0.96)
- Finding Good Configurations of Planar Primitives in Unorganized Point Clouds (CVPR 2022 · similarity 0.88)
- QuadricFormer: Scene as Superquadrics for 3D Semantic Occupancy Prediction (NeurIPS 2025 · similarity 0.85)
- H3DNet: 3D Object Detection Using Hybrid Geometric Primitives (ECCV 2020 · similarity 0.85)
- Structure-Aware Surface Reconstruction via Primitive Assembly (ICCV 2023 · similarity 0.85)
- Connect-and-Slice: An Hybrid Approach for Reconstructing 3D Objects (CVPR 2020 · similarity 0.85)
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.
