# High-resolution Deep Convolutional Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1711.06491 · HTML: https://mlsanity.com/paper/1711.06491/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Nov 2017.

## Built on by (most cited first, 7 of 7)

- [Styleformer: Transformer based Generative Adversarial Networks with Style Vector](https://mlsanity.com/paper/2106.07023/) (2021)
- [Image Augmentation for Satellite Images](https://mlsanity.com/paper/2207.14580/) (2022)
- [The Nuts and Bolts of Adopting Transformer in GANs](https://mlsanity.com/paper/2110.13107/) (2021)
- [PetroGAN: A novel GAN-based approach to generate realistic, label-free petrographic datasets](https://mlsanity.com/paper/2204.05114/) (2022)
- [Generative Adversarial Networks for anonymous Acneic face dataset generation](https://mlsanity.com/paper/2211.04214/) (2022)
- [Generation of Synthetic Images for Pedestrian Detection Using a Sequence of GANs](https://mlsanity.com/paper/2401.07370/) (2024)
- [Hardware-Friendly Diffusion Models with Fixed-Size Reusable Structures for On-Device Image Generation](https://mlsanity.com/paper/2411.06119/) (2024)

## Abstract (arXiv)

Generative Adversarial Networks (GANs) [Goodfellow et al. 2014] convergence in a high-resolution setting with a computational constrain of GPU memory capacity has been beset with difficulty due to the known lack of convergence rate stability. In order to boost network convergence of DCGAN (Deep Convolutional Generative Adversarial Networks) [Radford et al. 2016] and achieve good-looking high-resolution results we propose a new layered network, HDCGAN, that incorporates current state-of-the-art techniques for this effect. Glasses, a mechanism to arbitrarily improve the final GAN generated results by enlarging the input size by a telescope zeta is also presented. A novel bias-free dataset, Curt'o & Zarza, containing human faces from different ethnical groups in a wide variety of illumination conditions and image resolutions is introduced. Curt'o is enhanced with HDCGAN synthetic images, thus being the first GAN augmented dataset of faces. We conduct extensive experiments on CelebA [Liu et al. 2015], CelebA-hq [Karras et al. 2018] and Curt'o. HDCGAN is the current state-of-the-art in synthetic image generation on CelebA achieving a MS-SSIM of 0.1978 and a FR'ECHET Inception Distance of 8.44.