Research map / 3D vision / Face and shape
3D Equivariant Graph Implicit Functions
Yunlu Chen, Basura Fernando, Hakan Bilen, Matthias Nießner, Efstratios Gavves
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 multi-scale graph sampling (ablation) | GraphONet · Synthetic Room | IoU: 0.859 -> 0.883 | Improved |
| add multi-scale graph sampling (ablation) | GraphONet · ShapeNet | mean IoU: 0.897 -> 0.904 | Improved |
| add multi-scale graph sampling (ablation) | E-GraphONet · Synthetic Room | IoU: 0.814 -> 0.848 | Improved |
| use graph encoder instead of PointNet encoder (ablation) | GraphONet · Synthetic Room | IoU: 0.826 -> 0.883 | Improved |
| use graph encoder instead of PointNet encoder (ablation) | GraphONet · ShapeNet | mean IoU: 0.887 -> 0.904 | Improved |
| use graph encoder instead of PointNet encoder (ablation) | ConvONet-3D · Synthetic Room | IoU: 0.847 -> 0.853 | No clear effect |
| use hybrid 50% vector channels instead of pure vector neurons (ablation) | VN-ONet-style equivariant model · ShapeNet | mIoU: 0.694 -> 0.719 | Improved |
| use hybrid 50% vector channels instead of pure vector neurons (ablation) | VN-PointNet · ModelNet40 | mAcc: 0.847 -> 0.856 | Improved |
| remove all vector channels (pure scalar) (ablation) | equivariant implicit model · ShapeNet | mIoU: 0.719 -> 0.408 | Hurt |
| add training rotation augmentation | GraphONet · ShapeNet | IoU: 0.846 -> 0.887 | Improved |
| use graph local features instead of grid features (GraphONet vs ConvONet-3D) | GraphONet · ShapeNet random rotation | IoU: 0.761 -> 0.846 | Improved |
| add SO(3) equivariant layers | GraphONet · ShapeNet canonical | mean IoU: 0.904 -> 0.890 | Hurt |
Closest papers by meaning
- $\mathrm{SE}(3)$-Equivariant Attention Networks for Shape Reconstruction in Function Space (ICLR 2023 · similarity 0.90)
- Learning 3D Equivariant Implicit Function with Patch-Level Pose-Invariant Representation (NeurIPS 2024 · similarity 0.89)
- On Explaining Equivariant Graph Networks via Improved Relevance Propagation (ICML 2025 · similarity 0.88)
- Neural Isometries: Taming Transformations for Equivariant ML (NeurIPS 2024 · similarity 0.87)
- Learning Generalizable Shape Completion with SIM(3) Equivariance (NeurIPS 2025 · similarity 0.87)
- Grounding Continuous Representations in Geometry: Equivariant Neural Fields (ICLR 2025 · similarity 0.87)
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.
