FDeID-Toolbox: Face De-Identification Toolbox

TL;DR

FDeID-Toolbox is a comprehensive, modular framework that standardizes data, methods, and evaluation for face de-identification, enabling reproducible and fair comparisons across diverse approaches and applications.

Contribution

It introduces a unified toolbox with standardized components and evaluation protocols to advance reproducible research in face de-identification.

Findings

Facilitates fair comparison of FDeID methods

Supports diverse downstream tasks and metrics

Enhances reproducibility and extensibility

Abstract

Face de-identification (FDeID) aims to remove personally identifiable information from facial images while preserving task-relevant utility attributes such as age, gender, and expression. It is critical for privacy-preserving computer vision, yet the field suffers from fragmented implementations, inconsistent evaluation protocols, and incomparable results across studies. These challenges stem from the inherent complexity of the task: FDeID spans multiple downstream applications (e.g., age estimation, gender recognition, expression analysis) and requires evaluation across three dimensions (e.g., privacy protection, utility preservation, and visual quality), making existing codebases difficult to use and extend. To address these issues, we present FDeID-Toolbox, a comprehensive toolbox designed for reproducible FDeID research. Our toolbox features a modular architecture comprising four core components: (1) standardized data loaders for mainstream benchmark datasets, (2) unified method implementations spanning classical approaches to SOTA generative models, (3) flexible inference pipelines, and (4) systematic evaluation protocols covering privacy, utility, and quality metrics. Through experiments, we demonstrate that FDeID-Toolbox enables fair and reproducible comparison of diverse FDeID methods under consistent conditions.