Research map / Point clouds / Point cloud classification
Equivariant Point Cloud Analysis via Learning Orientations for Message Passing
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 learned point-wise orientations to project relative coordinates in DGCNN | DGCNN · ModelNet40 normals, z/SO(3) | cosine distance: 0.32 -> 0.20 | Helped |
| Use learned point-wise orientations to project relative coordinates in DGCNN | DGCNN · ModelNet40 normals, SO(3)/SO(3) | cosine distance: 0.22 -> 0.20 | Helped |
| Use learned point-wise orientations to project relative coordinates | N-body model · 10 particles | MSE: 0.126 -> 0.103 | Helped |
| Use learned point-wise orientations to project relative coordinates | N-body model · 20 particles | MSE: 0.212 -> 0.206 | Helped |
| Use the equivariant DGCNN adaptation | DGCNN · ModelNet40 classification, z/z | accuracy: 91.8 -> 88.4 | Hurt |
Closest papers by meaning
- Beyond Canonicalization: How Tensorial Messages Improve Equivariant Message Passing (ICLR 2025 · similarity 0.89)
- Approximately Piecewise E(3) Equivariant Point Networks (ICLR 2024 · similarity 0.88)
- Fast, Expressive $\mathrm{SE}(n)$ Equivariant Networks through Weight-Sharing in Position-Orientation Space (ICLR 2024 · similarity 0.88)
- SIEVE: Overcoming Topological Obstruction in Equivariant Self-Supervised Learning (NeurIPS 2026 · similarity 0.87)
- Weisfeiler Leman for Euclidean Equivariant Machine Learning (ICML 2024 · similarity 0.86)
- SE(3)-bi-equivariant Transformers for Point Cloud Assembly (NeurIPS 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.