Research map / 3D vision / Face and shape
GIFT: A Real-Time and Scalable 3D Shape Search Engine
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use GIFT instead of the strongest listed baseline | 3D shape retrieval · ModelNet40 | AUC: 77.63% -> 83.10% | Helped |
| Use GIFT instead of the strongest listed baseline | 3D shape retrieval · ModelNet10 | MAP: 84.18% -> 91.12% | Helped |
| Use GIFT instead of LCDR-DBSVC | 3D shape retrieval · SHREC14LSGTB | FT: 0.528 -> 0.567 | Helped |
| Use GIFT instead of TLC | 3D shape retrieval · WM-SHREC07 | FT: 0.831 -> 0.949 | Helped |
| Fuse L5 and L7 features with re-ranking (ablation) | L5 and L7 retrieval on PSB · PSB | First Tier: 0.653 -> 0.688 | Helped |
| Set aggregation exponent alpha to 0.5 rather than 1 (ablation) | L5 + L7 re-ranking on PSB · PSB | First Tier: 0.688 -> 0.692 | Helped |
| Add neighbor augmentation (ablation) | L5 + L7 re-ranking on PSB · PSB | First Tier: 0.692 -> 0.717 | Helped |
| Replace exact Hausdorff matching with approximate F-IF matching (ablation) | L5 + L7 with re-ranking on PSB · PSB | First Tier: 0.717 -> 0.712 | Hurt |
| Use approximate Hausdorff matching with F-IF rather than exact matching | L7 matching on SHREC14LSGTB · SHREC14LSGTB | query time: $4.82s$ -> $63.14ms$ | Helped |
Closest papers by meaning
- Duoduo CLIP: Efficient 3D Understanding with Multi-View Images (ICLR 2025 · similarity 0.83)
- KP-RED: Exploiting Semantic Keypoints for Joint 3D Shape Retrieval and Deformation (CVPR 2024 · similarity 0.83)
- Tango3D: Towards Alignment for Global and Local 2D-3D Correspondence (NeurIPS 2026 · similarity 0.83)
- PyTorchGeoNodes: Enabling Differentiable Shape Programs for 3D Shape Reconstruction (CVPR 2025 · similarity 0.83)
- MetaFind: Scene-Aware 3D Asset Retrieval for Coherent Metaverse Scene Generation (NeurIPS 2025 · similarity 0.83)
- SpiderMatch: 3D Shape Matching with Global Optimality and Geometric Consistency (CVPR 2024 · similarity 0.82)
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.