Research map / Point clouds / Shape and surface completion
$\mathrm{SE}(3)$-Equivariant Attention Networks for Shape Reconstruction in Function Space
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 |
|---|---|---|---|
| add type-2 representations to both encoder and decoder instead of using only types 0–1 (ablation) | TFOnet · ShapeNet, I/I | IoU: 73.8% -> 78% | Helped |
| add type-2 representations to both encoder and decoder instead of using only types 0–1 (ablation) | TFOnet · ShapeNet, I/SO(3) | IoU: 73.8% -> 78% | Helped |
| add type-2 representations to both encoder and decoder instead of using only types 0–1 (ablation) | TFOnet · ShapeNet, SO(3)/SO(3) | IoU: 73.9% -> 78% | Helped |
| add type-2 representations to the decoder, keeping the encoder up to type-2 (ablation) | TFOnet · ShapeNet, I/I | IoU: 77.4% -> 78% | Helped |
| add type-2 representations to the decoder, keeping the encoder up to type-2 (ablation) | TFOnet · ShapeNet, I/SO(3) | IoU: 77.4% -> 78% | Helped |
| add type-2 representations to the decoder, keeping the encoder up to type-2 (ablation) | TFOnet · ShapeNet, SO(3)/SO(3) | IoU: 77.3% -> 78% | Helped |
| use SE(3)-equivariant local attention with higher-order representations rather than GraphOnet | TFOnet · ShapeNet, I/SO(3) | IoU: 73.2% -> 78% | Helped |
| use SE(3)-equivariant local attention with higher-order representations rather than GraphOnet | TFOnet · ShapeNet, SO(3)/SO(3) | IoU: 73.2% -> 78% | Helped |
Closest papers by meaning
- Equivariant Point Network for 3D Point Cloud Analysis (CVPR 2021 · similarity 0.93)
- E2PN: Efficient SE(3)-Equivariant Point Network (CVPR 2023 · similarity 0.91)
- SIEVE: Overcoming Topological Obstruction in Equivariant Self-Supervised Learning (NeurIPS 2026 · similarity 0.89)
- Approximately Piecewise E(3) Equivariant Point Networks (ICLR 2024 · similarity 0.88)
- SE(3)-bi-equivariant Transformers for Point Cloud Assembly (NeurIPS 2024 · similarity 0.87)
- Fast, Expressive $\mathrm{SE}(n)$ Equivariant Networks through Weight-Sharing in Position-Orientation Space (ICLR 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.