Research map / Point clouds / Point cloud classification
Steerable 3D Spherical Neurons
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 |
|---|---|---|---|
| Construct steerable spherical filter-bank units from the trained ancestor using known rotations | MLGP ancestor · 3D Tetris and UTKinect-Action3D test | accuracy (%): 100.0±0.0 vs 100.0±0.0 (3D Tetris, noise 0.00); 92.9±0.0 vs 92.9±0.0 (skeleton, noise 0.000) | No clear effect |
| Add input noise to the rotated point clouds | Steerable model · 3D Tetris | accuracy (%): 100.0±0.0 -> 94.9±7.7 | Hurt |
| Add input noise to the rotated point clouds | Steerable model · UTKinect-Action3D test | accuracy (%): 92.9±0.0 -> 72.0±0.7 | Hurt |
| Add input noise to the rotated point clouds | Steerable model · 3D Tetris | L1 activation distance: 0.00±0.00 -> 3.33±0.48 | Hurt |
| Add input noise to the rotated point clouds | Steerable model · UTKinect-Action3D test | L1 activation distance: 0.00±0.00 -> 5.30±0.02 | Hurt |
Closest papers by meaning
- TetraSphere: A Neural Descriptor for O(3)-Invariant Point Cloud Analysis (CVPR 2024 · similarity 0.89)
- Learning to Orient Surfaces by Self-supervised Spherical CNNs (NeurIPS 2020 · similarity 0.88)
- PDO-s3DCNNs: Partial Differential Operator Based Steerable 3D CNNs (ICML 2022 · similarity 0.88)
- Neural Isometries: Taming Transformations for Equivariant ML (NeurIPS 2024 · similarity 0.86)
- Steerable Transformers for Volumetric Data (ICML 2025 · similarity 0.85)
- Clifford-Steerable Convolutional Neural Networks (ICML 2024 · 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.