---
title: "Face De-Identification: A Domain-Centric Survey from Capture to Processing"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.25926v1"
permalink: "https://feed.astralor.com/items/itm_b1e32faf941d1a5790a63ea9"
published: "2026-07-28T16:15:12.000Z"
score: 81
channel: "ai"
tags: ["Face De-Identification","Sensor","Computer Vision","Responsible AI","Privacy Protection"]
---

# Face De-Identification: A Domain-Centric Survey from Capture to Processing

## AI commentary

> This survey is highly timely as global privacy regulations (e.g., GDPR) tighten, making face de-identification a necessity. Its full-chain perspective from sensor to algorithm is especially enlightening for product managers and tech decision-makers—for instance, integrating sensor-level de-identification in surveillance cameras can significantly reduce downstream complexity and compliance risk. I recommend all teams dealing with facial data to read it carefully, especially the evaluation benchmark section, which can help establish internal testing standards.

## At a glance

This survey provides the first unified overview of the full data acquisition pipeline for face de-identification (De-ID), covering physical, sensor, and digital domains. Through a domain-centric lens, it systematically analyzes methodologies, technical progress, and distinct challenges at each stage, reviews existing evaluation protocols, and highlights the urgent need for standardized benchmarks. It identifies key open problems and emerging research directions. An accompanying project page curates relevant literature, datasets, and open-source code.

## Key points

- First unified overview of face de-identification spanning the entire acquisition pipeline: physical, sensor, and digital domains.
- Systematic analysis of methods, progress, and challenges per domain, including digital pixel-level modification, in-sensor privacy integration, and physical wearable camouflage.
- Evaluation of existing protocols, highlighting the lack of standardized benchmarks as a major bottleneck.
- Key open problems and future directions identified, with an open-source project page.

## Full text

Face de-identification (De-ID) aims to remove or conceal personally identifiable facial features in images or videos to prevent identity recognition while preserving utility for downstream tasks. With the rising emphasis on data privacy and responsible AI, face De-ID has emerged as an active research area spanning computer vision and privacy-preserving communities. Early approaches, and many contemporary ones, operate in the digital domain by modifying pixel-level or appearance-level features through post-capture processing. Recent advances extend face De-ID beyond post-processing by integrating privacy mechanisms directly into sensors during image acquisition, bridging sensing systems and downstream vision algorithms. In parallel, physical-domain methods explore wearable accessories and materials that conceal identity information in real-world environments prior to capture. In this survey, we present the first unified overview that spans the full data acquisition pipeline, encompassing the physical, sensor, and digital domains. Through this domain-centric lens, we systematically analyze current methodologies, technical progress, and the distinct challenges inherent to each stage. We then review and organize existing evaluation protocols, examining current practices and highlighting the critical need for standardized, comprehensive benchmarks. Finally, we identify key open problems and outline emerging research directions to guide future work in this rapidly evolving field. To support ongoing research, we maintain a project page that organizes relevant literature with collected datasets and open source code: https://github.com/CV-AC/Awesome-FaceDe-ID.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_b1e32faf941d1a5790a63ea9