A state-of-the-art review on image synthesis with generative adversarial networks

L Wang, W Chen, W Yang, F Bi, FR Yu - Ieee Access, 2020 - ieeexplore.ieee.org
Generative Adversarial Networks (GANs) have achieved impressive results in various image
synthesis tasks, and are becoming a hot topic in computer vision research because of the …

Gan-leaks: A taxonomy of membership inference attacks against generative models

D Chen, N Yu, Y Zhang, M Fritz - Proceedings of the 2020 ACM SIGSAC …, 2020 - dl.acm.org
Deep learning has achieved overwhelming success, spanning from discriminative models to
generative models. In particular, deep generative models have facilitated a new level of …

Attributing fake images to gans: Learning and analyzing gan fingerprints

N Yu, LS Davis, M Fritz - Proceedings of the IEEE/CVF …, 2019 - openaccess.thecvf.com
Abstract Recent advances in Generative Adversarial Networks (GANs) have shown
increasing success in generating photorealistic images. But they also raise challenges to …

Generative adversarial network applications in industry 4.0: A review

C Abou Akar, R Abdel Massih, A Yaghi, J Khalil… - International Journal of …, 2024 - Springer
The breakthrough brought by generative adversarial networks (GANs) in computer vision
(CV) applications has gained a lot of attention in different fields due to their ability to capture …

Unleashing transformers: Parallel token prediction with discrete absorbing diffusion for fast high-resolution image generation from vector-quantized codes

S Bond-Taylor, P Hessey, H Sasaki, TP Breckon… - … on Computer Vision, 2022 - Springer
Whilst diffusion probabilistic models can generate high quality image content, key limitations
remain in terms of both generating high-resolution imagery and their associated high …

Dual contrastive loss and attention for gans

N Yu, G Liu, A Dundar, A Tao… - Proceedings of the …, 2021 - openaccess.thecvf.com
Abstract Generative Adversarial Networks (GANs) produce impressive results on
unconditional image generation when powered with large-scale image datasets. Yet …

Learning a neural 3d texture space from 2d exemplars

P Henzler, NJ Mitra, T Ritschel - Proceedings of the IEEE …, 2020 - openaccess.thecvf.com
We suggest a generative model of 2D and 3D natural textures with diversity, visual fidelity
and at high computational efficiency. This is enabled by a family of methods that extend …

Beyond the spectrum: Detecting deepfakes via re-synthesis

Y He, N Yu, M Keuper, M Fritz - arXiv preprint arXiv:2105.14376, 2021 - arxiv.org
The rapid advances in deep generative models over the past years have led to highly
{realistic media, known as deepfakes,} that are commonly indistinguishable from real to …

Repmix: Representation mixing for robust attribution of synthesized images

T Bui, N Yu, J Collomosse - European Conference on Computer Vision, 2022 - Springer
Abstract Rapid advances in Generative Adversarial Networks (GANs) raise new challenges
for image attribution; detecting whether an image is synthetic and, if so, determining which …

A sliced wasserstein loss for neural texture synthesis

E Heitz, K Vanhoey, T Chambon… - Proceedings of the …, 2021 - openaccess.thecvf.com
We address the problem of computing a textural loss based on the statistics extracted from
the feature activations of a convolutional neural network optimized for object recognition (eg …