1 code implementation • 8 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.
1 code implementation • 6 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.
1 code implementation • 17 Nov 2022 • Håkon Hukkelås, Frank Lindseth
Generative Adversarial Networks (GANs) are widely adapted for anonymization of human figures.
1 code implementation • 6 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.
1 code implementation • 2 Nov 2020 • Håkon Hukkelås, Frank Lindseth, Rudolf Mester
We propose (layer-wise) feature imputation of the missing input values to a convolution.
2 code implementations • 10 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)