Research map / 3D vision / Face and shape
GEOBIT: A Geodesic-Based Binary Descriptor Invariant to Non-Rigid Deformations for RGB-D Images
Erickson R. Nascimento, Guilherme Potje, Renato Martins, Felipe Cadar, Mario F. M. Campos, Ruzena Bajcsy
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 geodesic-isocurve binary descriptor instead of DaLI | deformable RGB-D keypoint matching · Lascaux | recognition rate: 0.65 -> 0.82 | Improved |
| add geodesic-isocurve binary descriptor instead of DaLI | deformable RGB-D keypoint matching · Van Gogh | AUC: 0.50 -> 0.46 | No clear effect |
| use the proposed descriptor instead of DaLI across datasets | deformable RGB-D keypoint matching · Table 1 datasets | recognition rate and AUC: 4.5 times faster | Improved |
| add the depth-pyramid smoothing step before heat flow (ablation) | GEOBIT · Kanagawa with noise | relative recognition rate: gains increase as noise standard deviation increases | Improved |
| use Gaussian instead of uniform distribution of binary test pairs (ablation) | GEOBIT · Binary test pattern | recognition rate: slightly higher recognition rates | Improved |
| add geodesic descriptor instead of TFeat CNN descriptor | real datasets · Real-world deformable objects | accuracy: 4.5% p.p. | Improved |
Later papers that compared with this method
1 later accepted paper reports GeoBit as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Extracting Deformation-Aware Local Features by Learning to Deform (NeurIPS 2021 · better on 10 of 12 shared results)
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
- Extracting Deformation-Aware Local Features by Learning to Deform (NeurIPS 2021 · similarity 0.89)
- RDD: Robust Feature Detector and Descriptor using Deformable Transformer (CVPR 2025 · similarity 0.85)
- Spectral Meets Spatial: Harmonising 3D Shape Matching and Interpolation (CVPR 2024 · similarity 0.84)
- Hybrid Functional Maps for Crease-Aware Non-Isometric Shape Matching (CVPR 2024 · similarity 0.84)
- MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Images (CVPR 2024 · similarity 0.84)
- DV-Matcher: Deformation-based Non-rigid Point Cloud Matching Guided by Pre-trained Visual Features (CVPR 2025 · 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.
