Research map / Point clouds / Point cloud classification
ZZ-Net: A Universal Rotation Equivariant Architecture for 2D Point Clouds
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 |
|---|---|---|---|
| Use the three-unit deep ZZ-net instead of the broad single-unit ZZ-net | ZZ-net · Rotation estimation with noisy point clouds | within-threshold rotation accuracy | Helped |
| Use rotation-equivariant ZZ-net rather than ACNe | Essential matrix estimation · Reichstag, test rotation up to 30° | mAP at 20°: 0.25 -> 0.26 | Helped |
| Use rotation-equivariant ZZ-net rather than ACNe | Essential matrix estimation · Reichstag, test rotation up to 60° or 180° | mAP at 20°: 0.15 -> 0.26; 0.038 -> 0.26 | Helped |
| Use rotation-equivariant ZZ-net rather than ACNe | Essential matrix estimation · Reichstag, unrotated test data | mAP at 20°: 0.67 -> 0.26 | Hurt |
Closest papers by meaning
- On the Universality of Rotation Equivariant Point Cloud Networks (ICLR 2021 · similarity 0.93)
- Equivariant Point Network for 3D Point Cloud Analysis (CVPR 2021 · similarity 0.89)
- Approximately Piecewise E(3) Equivariant Point Networks (ICLR 2024 · similarity 0.88)
- Local-consistent Transformation Learning for Rotation-invariant Point Cloud Analysis (CVPR 2024 · similarity 0.87)
- 3D Equivariant Pose Regression via Direct Wigner-D Harmonics Prediction (NeurIPS 2024 · similarity 0.86)
- TetraSphere: A Neural Descriptor for O(3)-Invariant Point Cloud Analysis (CVPR 2024 · similarity 0.86)
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.