DC-Art-GAN: Stable Procedural Content Generation using DC-GANs for Digital Art

TL;DR

This paper explores using DC-GANs for stable, realistic digital art creation, addressing training challenges and comparing architectures to improve generative quality for digital art and NFTs.

Contribution

It introduces techniques for stable DC-GAN training, compares architectures, and emphasizes preprocessing's role in generating realistic digital art images.

Findings

Optimal DC-GAN architecture identified for stable art generation

Preprocessing significantly improves GAN training stability

Generated images demonstrate realistic and diverse digital art

Abstract

Art is an artistic method of using digital technologies as a part of the generative or creative process. With the advent of digital currency and NFTs (Non-Fungible Token), the demand for digital art is growing aggressively. In this manuscript, we advocate the concept of using deep generative networks with adversarial training for a stable and variant art generation. The work mainly focuses on using the Deep Convolutional Generative Adversarial Network (DC-GAN) and explores the techniques to address the common pitfalls in GAN training. We compare various architectures and designs of DC-GANs to arrive at a recommendable design choice for a stable and realistic generation. The main focus of the work is to generate realistic images that do not exist in reality but are synthesised from random noise by the proposed model. We provide visual results of generated animal face images (some pieces of evidence showing a blend of species) along with recommendations for training, architecture and design choices. We also show how training image preprocessing plays a massive role in GAN training.