Improving 3D Finger Traits Recognition via Generalizable Neural Rendering
Not on the map. Why?
Abstract (arXiv)
3D biometric techniques on finger traits have become a new trend and have demonstrated a powerful ability for recognition and anti-counterfeiting. Existing methods follow an explicit 3D pipeline that reconstructs the models first and then extracts features from 3D models. However, these explicit 3D methods suffer from the following problems: 1) Inevitable information dropping during 3D reconstruction; 2) Tight coupling between specific hardware and algorithm for 3D reconstruction. It leads us to a question: Is it indispensable to reconstruct 3D information explicitly in recognition tasks? Hence, we consider this problem in an implicit manner, leaving the nerve-wracking 3D reconstruction problem for learnable neural networks with the help of neural radiance fields (NeRFs). We propose FingerNeRF, a novel generalizable NeRF for 3D finger biometrics. To handle the shape-radiance ambiguity problem that may result in incorrect 3D geometry, we aim to involve extra geometric priors based on the correspondence of binary finger traits like fingerprints or finger veins. First, we propose a novel Trait Guided Transformer (TGT) module to enhance the feature correspondence with the guidance of finger traits. Second, we involve extra geometric constraints on the volume rendering loss with the proposed Depth Distillation Loss and Trait Guided Rendering Loss. To evaluate the performance of the proposed method on different modalities, we collect two new datasets: SCUT-Finger-3D with finger images and SCUT-FingerVein-3D with finger vein images. Moreover, we also utilize the UNSW-3D dataset with fingerprint images for evaluation. In experiments, our FingerNeRF can achieve 4.37% EER on SCUT-Finger-3D dataset, 8.12% EER on SCUT-FingerVein-3D dataset, and 2.90% EER on UNSW-3D dataset, showing the superiority of the proposed implicit method in 3D finger biometrics.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 20 of its 50 references that are in the map. First posted on arXiv 12 Oct 2024.
Builds on
20 of 50 references.
References · 20
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
- 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
- 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
- 2020Point Transformercited by 1,470
- 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,136
- 2020Neural Sparse Voxel Fieldscited by 959
- 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 788
- 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 735
- 2020PCT: Point cloud transformercited by 732
- 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 379
- 2018Deep Face Recognition: A Surveycited by 276
- 2019Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inferencecited by 254
8 more
- 2019Neural Volumes: Learning Dynamic Renderable Volumes from Imagescited by 173
- 2020Deep Reflectance Volumes: Relightable Reconstructions from Multi-View Photometric Imagescited by 98
- 2020Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloudcited by 71
- 2019Geometry Sharing Network for 3D Point Cloud Classification and Segmentationcited by 33
- 2021Self-supervised Multi-view Stereo via Effective Co-Segmentation and Data-Augmentationcited by 31
- 2021Digging into Uncertainty in Self-supervised Multi-view Stereocited by 31
- 2022Monocular 3D Fingerprint Reconstruction and Unwarpingcited by 11
- 2023Advancing 3D finger knuckle recognition via deep feature learningcited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.