Research map / 3D vision / Face and shape
Improving 3D Finger Traits Recognition via Generalizable Neural Rendering
Hongbin Xu, Junduan Huang, Yuer Ma, Zifeng Li, Wenxiong Kang
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 |
|---|---|---|---|
| use implicit sparse-view FingerNeRF instead of explicit dense reconstruction (geometry only) | finger recognition pipeline · SCUT-Finger-3D | EER (%): 36.81% -> 22.60% | Improved |
| add texture (color) to geometry (ablation) | FingerNeRF · SCUT-Finger-3D | EER (%): 22.60% -> 15.60% | Improved |
| render both image and depth instead of image only (ablation) | FingerNeRF · SCUT-Finger-3D | EER (%): 22.40% -> 15.60% | Improved |
| render both image and depth instead of depth only (ablation) | FingerNeRF · SCUT-Finger-3D | mAP (%): 45.98% -> 53.97% | Improved |
| render 20 views instead of 8 (ablation) | FingerNeRF · SCUT-Finger-3D | EER (%): 21.20% -> 15.60% | Improved |
| render 20 views instead of 16 (ablation) | FingerNeRF · SCUT-Finger-3D | mAP (%): 57.20% -> 53.97% | Hurt |
| add depth supervision loss to MVSNeRF (ablation) | FingerNeRF · SCUT-Finger-3D | test PSNR: 29.09 -> 29.39 | Improved |
| add trait-guided loss (ablation) | FingerNeRF · SCUT-Finger-3D | test PSNR: 29.39 -> 31.24 | Improved |
| add trait-guided transformer (ablation) | FingerNeRF · SCUT-Finger-3D | test PSNR: 31.24 -> 32.27 | Improved |
| add depth supervision loss to MVSNeRF (ablation) | FingerNeRF · UNSW-3D | test PSNR: 29.09 -> 28.49 | Mixed |
| add trait-guided transformer (ablation) | FingerNeRF · SCUT-FingerVein-3D | test PSNR: 26.61 -> 26.67 | No clear effect |
| use FingerNeRF instead of MVSNeRF for novel view synthesis | FingerNeRF · SCUT-Finger-3D | test PSNR: 29.09 -> 32.27 | Improved |
Closest papers by meaning
- Study of Full-View Finger Vein Biometrics on Redundancy-Compensated 3D Reconstruction and Frequency-Spatial Coupling Feature Extraction (TPAMI 2026 · similarity 0.86)
- Bridging Dimensions in Fingerprints to Advance Distinctiveness: Recovering 3D Minutiae From a Single Contactless 2D Fingerprint Image (TPAMI 2025 · similarity 0.86)
- Contactless Biometric Identification Using 3D Finger Knuckle Patterns (TPAMI 2019 · similarity 0.84)
- 3D Visibility-Aware Generalizable Neural Radiance Fields for Interacting Hands (AAAI 2024 · similarity 0.82)
- Towards Explainable and Unprecedented Accuracy in Matching Challenging Finger Crease Patterns (CVPR 2025 · similarity 0.82)
- Reconstructing Hands in 3D with Transformers (CVPR 2024 · similarity 0.81)
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.
