Research map / Point clouds / Shape and surface completion
GFrames: Gradient-Based Local Reference Frame for 3D Shape Matching
Simone Melzi, Riccardo Spezialetti, Federico Tombari, Michael M. Bronstein, Luigi Di Stefano, Emanuele Rodola
Check 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 |
|---|---|---|---|
| Replace the SHOT local frame with GFrames using squared Fiedler vector | SHOT descriptor · TOSCA dog | AUC: 65.2 -> 71.5 | Improved |
| Use DEP instead of squared Fiedler vector as the scalar function (ablation) | GFrames with SHOT descriptor · TOSCA dog | AUC: 71.5 -> 70 | Hurt |
| Use Gaussian curvature instead of squared Fiedler vector as the scalar function (ablation) | GFrames with SHOT descriptor · TOSCA dog | AUC: 71.5 -> 61.6 | Hurt |
| Use mean curvature instead of squared Fiedler vector as the scalar function (ablation) | GFrames with SHOT descriptor · TOSCA dog | AUC: 71.5 -> 62.2 | Hurt |
| Replace SHOT with GFrames using squared Fiedler vector | SHOT descriptor · FAUST inter | AUC: 58 -> 62.7 | Improved |
| Replace SHOT with GFrames using squared Fiedler vector | SHOT descriptor · TOSCA horse | AUC: 69.3 -> 73.3 | Improved |
| Replace SHOT with GFrames using squared Fiedler vector | SHOT descriptor · TOPKIDS | AUC: 42.2 -> 53.1 | Improved |
| Replace SHOT with GFrames using squared Fiedler vector | SHOT descriptor · FAUST intra | AUC: 71.1 -> 77.4 | Improved |
| Replace SHOT with GFrames using squared Fiedler vector | SHOT descriptor · FARM cross-dataset | AUC: 27 -> 30.9 | Improved |
| Use Gaussian curvature instead of squared Fiedler vector as the scalar function (ablation) | GFrames with SHOT descriptor · FARM cross-dataset | AUC: 30.9 -> 26.5 | Hurt |
| Use mean curvature instead of squared Fiedler vector as the scalar function (ablation) | GFrames with SHOT descriptor · FARM cross-dataset | AUC: 30.9 -> 24 | Hurt |
| Use STED-based GFrames instead of SHOT LRF | SHOT descriptor on Angel point clouds · Angel point clouds | MeanCos: 0.19 -> 0.69 | Improved |
Closest papers by meaning
- DWKS: A Local Descriptor of Deformations Between Meshes and Point Clouds (ICCV 2021 · similarity 0.87)
- Local-consistent Transformation Learning for Rotation-invariant Point Cloud Analysis (CVPR 2024 · similarity 0.86)
- Fast Globally Optimal and Geometrically Consistent 3D Shape Matching (ICCV 2025 · similarity 0.85)
- Spectral Meets Spatial: Harmonising 3D Shape Matching and Interpolation (CVPR 2024 · similarity 0.85)
- Partial-to-Partial Shape Matching with Geometric Consistency (CVPR 2024 · similarity 0.84)
- HOPE: Shape Matching Via Aligning Different K-hop Neighbourhoods (NeurIPS 2024 · 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.
