Privacy-Aware Meta-Optics for Person Detection.

The ubiquitous use of computer vision technologies in our personal lives has led to privacy concerns. This paper presents a computational camera that optically filters out private attributes such as identity and still enables downstream vision task of person detection. Our approach involves replacing a traditional lens in an imaging setup with broadband meta-optics (MOs), the parameters of which are optimized in an end-to-end fashion using a differentiable look-up table for the MO and a person detection neural network. Privacy is introduced to the optimization pipeline using a novel and computationally inexpensive private Strehl integral regularization to preserve low-frequency details while filtering out high-frequency details that contain facial identity information. We experimentally validate our approach using captures from our privacy-aware meta-optics and demonstrate that this method achieves a better privacy utility trade-off compared to existing techniques. As such, we present the first privacy-aware broadband meta-optics for person detection.