Privacy-Aware Meta-Optics for Person Detection
Open Access
- 13 March 2026
- journal article
- Published by American Chemical Society (ACS) in ACS Photonics
- Vol. 13 (7) , 1783-1789
Abstract
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.Keywords
Funding Information
- National Nanotechnology Coordination Office (NNCI-1542101)
- National Nanotechnology Coordination Office (NNCI-2025489)
This publication has 47 references indexed in Scilit:
- Nanofabrication for NanophotonicsACS Nano, 2025
- End‐to‐End Optimization of Metalens for Broadband and Wide‐Angle ImagingAdvanced Optical Materials, 2025
- Planar Large Field‐of‐View Spectral Imaging Based on Metasurface ArrayAdvanced Optical Materials, 2024
- Learning a Dynamic Privacy-Preserving Camera Robust to Inversion Attacks2024
- DecentNeRFs: Decentralized Neural Radiance Fields from Crowdsourced Images2024
- Minimalist Vision with Freeform Pixels2024
- End-to-end optimization of single-shot monocular metasurface camera for RGBD imagingOptics Communications, 2024
- All-Glass 100 mm Diameter Visible Metalens for Imaging the CosmosACS Nano, 2024
- Learning Phase Mask for Privacy-Preserving Passive Depth Estimation2022
- Microsoft COCO: Common Objects in Context2014