Research map / Detection and segmentation / Open-set and few-shot detection
Banana: Banach Fixed-Point Network for Pointcloud Segmentation with Inter-Part Equivariance
Congyue Deng, Jiahui Lei, Bokui Shen, Kostas Daniilidis, Leonidas Guibas
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 |
|---|---|---|---|
| Banana vs best baseline (VNN) on oven, unseen states | Banana · Shape2Motion oven unseen states | IoU: 53.64 -> 81.91 | Improved |
| Banana vs VNN on washing machine, unseen states | Banana · Shape2Motion washing machine unseen states | IoU: 47.35 -> 82.32 | Improved |
| Banana vs VNN on eyeglasses, unseen instances | Banana · Shape2Motion eyeglasses unseen instances | IoU: 62.98 -> 78.65 | Improved |
| Banana vs VNN on refrigerator, unseen instances | Banana · Shape2Motion refrigerator unseen instances | IoU: 48.49 -> 73.93 | Improved |
| global SE(3) equivariance (VNN) vs non-equivariant PointNet | VNN · Shape2Motion oven unseen states | IoU: 44.08 -> 53.64 | Improved |
| DGCNN vs PointNet | DGCNN · Shape2Motion eyeglasses unseen states | IoU: 38.96 -> 33.35 | Hurt |
| replace part-level equivariance by PCA canonicalization (ablation) | Banana · Shape2Motion oven | IoU | Hurt |
| replace part-level equivariance by translation-only canonicalization with VNN (ablation) | Banana · Shape2Motion oven | IoU | Hurt |
| increase noise level in initial segmentation y(0) (ablation) | PCA canonicalization variant · Shape2Motion oven | IoU | Hurt |
| increase noise level in initial segmentation y(0) (ablation) | Banana · Shape2Motion oven | IoU | No clear effect |
Closest papers by meaning
- Equivariant Point Network for 3D Point Cloud Analysis (CVPR 2021 · similarity 0.89)
- Approximately Piecewise E(3) Equivariant Point Networks (ICLR 2024 · similarity 0.89)
- Learning Coordinate-based Convolutional Kernels for Continuous SE(3) Equivariant and Efficient Point Cloud Analysis (CVPR 2026 · similarity 0.87)
- Rectified Point Flow: Generic Point Cloud Pose Estimation (NeurIPS 2025 · similarity 0.87)
- Probing Equivariance and Symmetry Breaking in Convolutional Networks (NeurIPS 2025 · similarity 0.86)
- Point Cloud Part Editing: Segmentation, Generation, Assembly, and Selection (AAAI 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.
