Research map / 3D vision / Face and shape
LBONet: Supervised Spectral Descriptors for Shape Analysis
Oguzhan Yigit, Richard C. Wilson
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 VoronoiNet alone (ablation) | LBONet frontend · Human segmentation (ablation, shared MLP) | accuracy: 84.1 -> 84.6 | Improved |
| add ALBONet alone (ablation) | LBONet frontend · Human segmentation (ablation, shared MLP) | accuracy: 84.1 -> 85.6 | Improved |
| add RiemannNet alone (ablation) | LBONet frontend · Human segmentation (ablation, shared MLP) | accuracy: 84.1 -> 86.9 | Improved |
| add ALBO+Net alone (ablation) | LBONet frontend · Human segmentation (ablation, shared MLP) | accuracy: 84.1 -> 88.1 | Improved |
| add VoronoiNet to ALBO+Net (ablation) | LBONet frontend · Human segmentation (ablation, shared MLP) | accuracy: 88.1 -> 89.9 | Improved |
| add RiemannNet to ALBO+Net and VoronoiNet (ablation) | LBONet frontend · Human segmentation (ablation, shared MLP) | accuracy: 89.9 -> 90.7 | Improved |
| add ALBONet to RiemannNet (ablation) | LBONet frontend · Human segmentation (ablation, shared MLP) | accuracy: 86.9 -> 87.8 | No clear effect |
| add LBONet to HKS-based network | baseline network · SHREC'14 real retrieval | First Tier: 64.81 -> 77.33 | Improved |
| add LBONet to HKS-based network | baseline network · SHREC'14 synthetic retrieval | First Tier: 81.40 -> 89.21 | Improved |
| add LBONet to HKS-based network | baseline network · SHREC'11 classification | accuracy: 98.0 -> 100.0 | Improved |
| add LBONet to HKS-based network | baseline network · ShapeNet Part segmentation | mean mIoU: 84.7 -> 89.4 | Improved |
| add LBONet to HKS-based network | baseline network · Human segmentation | accuracy: 91.1 -> 92.7 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- MVTN — MVTN: Multi-View Transformation Network for 3D Shape Recognition (ICCV 2021) · better on 0 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Learning Eigenstructures of Unstructured Data Manifolds (CVPR 2026 · similarity 0.88)
- Finsler-Laplace-Beltrami Operators with Application to Shape Analysis (CVPR 2024 · similarity 0.88)
- Hybrid Functional Maps for Crease-Aware Non-Isometric Shape Matching (CVPR 2024 · similarity 0.88)
- A Robust Local Spectral Descriptor for Matching Non-Rigid Shapes With Incompatible Shape Structures (CVPR 2019 · similarity 0.88)
- Spectral Shape Recovery and Analysis Via Data-driven Connections (IJCV 2021 · similarity 0.87)
- Task-Induced Riemannian Metrics for Vision Transformer Feature Spaces (NeurIPS 2026 · similarity 0.84)
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.
