Lensless cameras, innovatively replacing traditional lenses for ultra-thin, flat optics, encode light directly onto sensors, producing images that are not immediately recognizable. This compact, lightweight, and cost-effective imaging solution offers inherent privacy advantages, making it attractive for privacy-sensitive applications like face verification. Typical lensless face verification adopts a two-stage process of reconstruction followed by verification, incurring privacy risks from reconstructed faces and high computational costs. This paper presents an end-to-end optimization approach for privacy-preserving face verification directly on encoded lensless captures, ensuring that the entire software pipeline remains encoded with no visible faces as intermediate results. To achieve this, we propose several techniques to address unique challenges from the lensless setup which precludes traditional face detection and alignment. Specifically, we propose a face center alignment scheme, an augmentation curriculum to build robustness against variations, and a knowledge distillation method to smooth optimization and enhance performance. Evaluations under both simulation and real environment demonstrate our method outperforms two-stage lensless verification while enhancing privacy and efficiency.
Comparison of face verification approaches: Traditional lens-based verification (top), two-step reconstruct-and-verify lensless verification (middle), and our end-to-end lensless verification method (bottom). Our approach enhances privacy against software attacks as well as maintains robust face verification performance.
The top pathway simulates lensless imaging using a learnable mask to encode a facial scene into a sensor capture. The capture after face-center alignment is fed into the lensless verification student model. In the bottom pathway, the same scene is aligned by preprocessing, and then classified by a trained RGB teacher model. The teacher's soft labels and ground truth face IDs supervise the training of both the lensless student model and the learnable mask parameters.
@misc{cai2024lenslessface,
title={LenslessFace: An End-to-End Optimized Lensless System for Privacy-Preserving Face Verification},
author={Xin Cai and Hailong Zhang and Chenchen Wang and Wentao Liu and Jinwei Gu and Tianfan Xue},
year={2024},
eprint={2406.04129},
archivePrefix={arXiv},
primaryClass={cs.CV}
}