Search Results for author: Håkon Hukkelås

Found 6 papers, 6 papers with code

Does Image Anonymization Impact Computer Vision Training?

1 code implementation8 Jun 2023 Håkon Hukkelås, Frank Lindseth

Furthermore, we find that realistic anonymization can mitigate this decrease in performance, where our experiments reflect a minimal performance drop for face anonymization.

Face Anonymization Instance Segmentation +3

Synthesizing Anyone, Anywhere, in Any Pose

1 code implementation6 Apr 2023 Håkon Hukkelås, Frank Lindseth

Our main contribution is TriA-GAN, a keypoint-guided GAN that can synthesize Anyone, Anywhere, in Any given pose.

DeepPrivacy2: Towards Realistic Full-Body Anonymization

1 code implementation17 Nov 2022 Håkon Hukkelås, Frank Lindseth

Generative Adversarial Networks (GANs) are widely adapted for anonymization of human figures.

Face Anonymization

Realistic Full-Body Anonymization with Surface-Guided GANs

1 code implementation6 Jan 2022 Håkon Hukkelås, Morten Smebye, Rudolf Mester, Frank Lindseth

Recent work on image anonymization has shown that generative adversarial networks (GANs) can generate near-photorealistic faces to anonymize individuals.

Image Inpainting with Learnable Feature Imputation

1 code implementation2 Nov 2020 Håkon Hukkelås, Frank Lindseth, Rudolf Mester

We propose (layer-wise) feature imputation of the missing input values to a convolution.

Image Inpainting Imputation

DeepPrivacy: A Generative Adversarial Network for Face Anonymization

2 code implementations10 Sep 2019 Håkon Hukkelås, Rudolf Mester, Frank Lindseth

Our model is based on a conditional generative adversarial network, generating images considering the original pose and image background.

 Ranked #1 on Face Anonymization on 2019_test set (using extra training data)

Face Anonymization Generative Adversarial Network

Cannot find the paper you are looking for? You can Submit a new open access paper.