The reviewed record of science sign in
Pith

arxiv: 2302.08931 · v1 · pith:IIETVHUN · submitted 2023-02-17 · cs.CV

LDFA: Latent Diffusion Face Anonymization for Self-driving Applications

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:IIETVHUNrecord.jsonopen to challenge →

classification cs.CV
keywords facemethodsanonymizeddatadiffusionrecentanonymizationdatasets
0
0 comments X
read the original abstract

In order to protect vulnerable road users (VRUs), such as pedestrians or cyclists, it is essential that intelligent transportation systems (ITS) accurately identify them. Therefore, datasets used to train perception models of ITS must contain a significant number of vulnerable road users. However, data protection regulations require that individuals are anonymized in such datasets. In this work, we introduce a novel deep learning-based pipeline for face anonymization in the context of ITS. In contrast to related methods, we do not use generative adversarial networks (GANs) but build upon recent advances in diffusion models. We propose a two-stage method, which contains a face detection model followed by a latent diffusion model to generate realistic face in-paintings. To demonstrate the versatility of anonymized images, we train segmentation methods on anonymized data and evaluate them on non-anonymized data. Our experiment reveal that our pipeline is better suited to anonymize data for segmentation than naive methods and performes comparably with recent GAN-based methods. Moreover, face detectors achieve higher mAP scores for faces anonymized by our method compared to naive or recent GAN-based methods.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.