Research map / 3D vision / Face and shape
Monocular 3D Fingerprint Reconstruction and Unwarping
Zhe Cui, Jianjiang Feng, Jie Zhou
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 orientation and period auxiliary branches to gradient network (connected) (ablation) | gradient network · PolyU 3D | gradient error (mm/pixel): 0.7054 -> 0.4359 | Improved |
| add orientation and period auxiliary branches to gradient network (connected) (ablation) | gradient network · PolyU 3D | depth error (mm): 0.3502 -> 0.1802 | Improved |
| connect the orientation, period and gradient branches rather than parallel (ablation) | gradient network · PolyU 3D | depth error (mm): 0.2607 -> 0.1802 | Improved |
| apply ellipsoidal unwarping before matching (ablation) | fingerprint matching · UNSW CL-C all poses | EER (%): 15.79% -> 14.03% | Improved |
| unwarp horizontally only (cylindrical) | unwarping · UNSW CL-C | EER (%): 15.79% -> 16.28% | Hurt |
| unwarp in both directions instead of horizontally only (ablation) | unwarping · UNSW CL-CL | EER (%): 22.37% -> 20.18% | Improved |
| replace non-parametric unwarping with gradient-based unwarping (ablation) | unwarping · UNSW time cost | time cost (s): 140 -> 1.07 | Improved |
| add pose rotation to unwarping (ablation) | matching · UNSW CL-C all poses | EER (%): 14.03% -> 12.72% | Improved |
| add pose rotation to unwarping (ablation) | matching · UNSW CL-CL all poses | EER (%): 20.18 -> 14.12 | Improved |
| add unwarping (ablation) | matching · PolyU CL2C CL-CL | EER (%): 8.43% -> 6.45% | Improved |
| add unwarping (ablation) | matching · PolyU CL2C CL-C | EER (%): 6.45% -> 5.73% | Improved |
| use 3-pixel border removal in evaluation of numerical integration (ablation) | depth reconstruction · PolyU 3D numerical error | depth error (mm): 2.5210 -> 0.0141 | Improved |
Closest papers by meaning
- Bridging Dimensions in Fingerprints to Advance Distinctiveness: Recovering 3D Minutiae From a Single Contactless 2D Fingerprint Image (TPAMI 2025 · similarity 0.89)
- Synthesis of Multi-View 3D Fingerprints to Advance Contactless Fingerprint Identification (TPAMI 2023 · similarity 0.87)
- Contactless Biometric Identification Using 3D Finger Knuckle Patterns (TPAMI 2019 · similarity 0.83)
- A New Framework for Quality Assessment of High-Resolution Fingerprint Images (TPAMI 2016 · similarity 0.83)
- Towards Explainable and Unprecedented Accuracy in Matching Challenging Finger Crease Patterns (CVPR 2025 · similarity 0.81)
- BiTT: Bi-directional Texture Reconstruction of Interacting Two Hands from a Single Image (CVPR 2024 · similarity 0.78)
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.
