Research map / 3D vision / Face and shape
Leveraging SE(3) Equivariance for Learning 3D Geometric Shape Assembly
Ruihai Wu, Chenrui Tie, Yushi Du, Yan Zhao, Hao Dong
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 |
|---|---|---|---|
| add part correlations to SE(3)-equivariant part representations (ablation) | SE(3) shape assembly · Breaking Bad everyday | part accuracy (%): 18.4 -> 26.7 | Improved |
| add part correlations (ablation) | SE(3) shape assembly · Geometric Shape Mating | part accuracy (%): 80.5 -> 85.7 | Improved |
| add translation embedding (ablation) | SE(3) shape assembly · Breaking Bad everyday | part accuracy (%): 22.5 -> 26.7 | Improved |
| add translation embedding (ablation) | SE(3) shape assembly · Geometric Shape Mating | part accuracy (%): 84.3 -> 85.7 | Improved |
| add adversarial learning (ablation) | SE(3) shape assembly · Breaking Bad everyday | part accuracy (%): 23.7 -> 26.7 | Improved |
| add adversarial learning (ablation) | SE(3) shape assembly · Geometric Shape Mating | part accuracy (%): 82.6 -> 85.7 | Improved |
| use SE(3)-equivariant method instead of NSM | two-part mating · Geometric Shape Mating | RMSE (R) degree: 21.3 -> 15.9 | Improved |
| add part correlations on translation (ablation) | SE(3) shape assembly · Geometric Shape Mating | RMSE (T) x10^-2: 2.9 -> 2.7 | No clear effect |
Closest papers by meaning
- Disentangling Rotation and Translation from SE(3)-Equivariant Features for Shape Assembly (ECCV 2026 · similarity 0.90)
- Imagine: Image-Guided 3D Part Assembly with Structure Knowledge Graph (AAAI 2025 · similarity 0.88)
- Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing (CVPR 2024 · similarity 0.87)
- Deep SE(3)-Equivariant Geometric Reasoning for Precise Placement Tasks (ICLR 2024 · similarity 0.87)
- Two by Two: Learning Multi-Task Pairwise Objects Assembly for Generalizable Robot Manipulation (CVPR 2025 · similarity 0.86)
- Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature Finetuning (ICLR 2025 · 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.
