computer-vision-6

Face Anonymization

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in face-anonymization-6

Trend

Dataset

Best Model

Actions

2019_test set

LFW

Libraries

i

Use these libraries to find face-anonymization-6 models and implementations

Datasets

LFW

FDF

FDH

Subtasks

No subtasks available.

Most implemented papers

DeepPrivacy: A Generative Adversarial Network for Face Anonymization

R. Mester, Håkon Hukkelås, F. Lindseth•Mon Sep 09 2019

A novel architecture which is able to automatically anonymize faces in images while retaining the original data distribution is proposed, based on a conditional generative adversarial network, which generates highly realistic faces with a seamless transition between the generated face and the existing background.

280

Content

0

Paper Graph

CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks

L. Leal-Taix'e, Maxim Maximov, Ismail Elezi•Mon May 18 2020

CIAGAN, a model for image and video anonymization based on conditional generative adversarial networks, is proposed and developed, able to remove the identifying characteristics of faces and bodies while producing high-quality images and videos that can be used for any computer vision task, such as detection or tracking.

199 0

Paper Graph

GANonymization: A GAN-Based Face Anonymization Framework for Preserving Emotional Expressions

Fabio Hellmann, Silvan Mertes, Mohamed Benouis, Alexander Hustinx, Tzung-Chien Hsieh, C. Conati, P. Krawitz, Elisabeth André•Tue May 02 2023

GANonymization, a novel face anonymization framework with facial expression-preserving abilities, is introduced, based on a high-level representation of a face which is synthesized into an anonymized versionbased on a generative adversarial network (GAN).

29 0

Paper Graph

DeepPrivacy2: Towards Realistic Full-Body Anonymization

Håkon Hukkelås, F. Lindseth•Wed Nov 16 2022

This paper proposes a novel anonymization framework (DeepPrivacy2) for realistic anonymization of human figures and faces, and introduces a new large and diverse dataset for full-body synthesis, which significantly improves image quality and diversity of generated images.

81 0

Paper Graph

DisguisOR: holistic face anonymization for the operating room

N. Navab, Benjamin Busam, Tobias Czempiel, Lennart Bastian, T. D. Wang•Mon May 22 2023

The proposed DisguisOR addresses privacy on a scene level and has the potential to facilitate further research in SDS, enabling more realistic anonymization that is less detrimental to downstream tasks.

11 0

Paper Graph

Does Image Anonymization Impact Computer Vision Training?

Håkon Hukkelås, F. Lindseth•Wed May 31 2023

This study demonstrates that realistic anonymization can enable privacy-preserving computer vision development with minimal performance degradation across a range of important computer vision benchmarks.

31 0

Paper Graph

Adding a benchmark result helps the community track progress.