# Controlled GAN-Based Creature Synthesis via a Challenging Game Art Dataset -- Addressing the Noise-Latent Trade-Off

arXiv: https://arxiv.org/abs/2108.08922 · HTML: https://mlsanity.com/paper/2108.08922/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 33 references that are in the map.
- First posted on arXiv 19 Aug 2021.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Self-Attention Generative Adversarial Networks](https://mlsanity.com/paper/1805.08318/) (2018)
- [Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?](https://mlsanity.com/paper/1904.03189/) (2019)
- [GANSpace: Discovering Interpretable GAN Controls](https://mlsanity.com/paper/2004.02546/) (2020)
- [What is the State of Neural Network Pruning?](https://mlsanity.com/paper/2003.03033/) (2020)
- [Closed-Form Factorization of Latent Semantics in GANs](https://mlsanity.com/paper/2007.06600/) (2020)
- [GAN Inversion: A Survey](https://mlsanity.com/paper/2101.05278/) (2021)
- [Differentiable Augmentation for Data-Efficient GAN Training](https://mlsanity.com/paper/2006.10738/) (2020)
- [Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network](https://mlsanity.com/paper/1803.08664/) (2018)
- [Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights](https://mlsanity.com/paper/1702.03044/) (2017)
- [Few-shot Image Generation via Cross-domain Correspondence](https://mlsanity.com/paper/2104.06820/) (2021)
- [Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis](https://mlsanity.com/paper/2101.04775/) (2021)
- [Few-shot Image Generation with Elastic Weight Consolidation](https://mlsanity.com/paper/2012.02780/) (2020)
- [Transforming and Projecting Images into Class-conditional Generative Networks](https://mlsanity.com/paper/2005.01703/) (2020)
- [A Fully Progressive Approach to Single-Image Super-Resolution](https://mlsanity.com/paper/1804.02900/) (2018)
- [Towards the Automatic Anime Characters Creation with Generative Adversarial Networks](https://mlsanity.com/paper/1708.05509/) (2017)
- [Instance Selection for GANs](https://mlsanity.com/paper/2007.15255/) (2020)
- [On Noise Injection in Generative Adversarial Networks](https://mlsanity.com/paper/2006.05891/) (2020)

## Built on by (most cited first, 2 of 2)

- [Dequantization and Color Transfer with Diffusion Models](https://mlsanity.com/paper/2307.02698/) (2023)
- [Looks Like Magic: Transfer Learning in GANs to Generate New Card Illustrations](https://mlsanity.com/paper/2205.14442/) (2022)

## Abstract (arXiv)

The state-of-the-art StyleGAN2 network supports powerful methods to create and edit art, including generating random images, finding images "like" some query, and modifying content or style. Further, recent advancements enable training with small datasets. We apply these methods to synthesize card art, by training on a novel Yu-Gi-Oh dataset. While noise inputs to StyleGAN2 are essential for good synthesis, we find that coarse-scale noise interferes with latent variables on this dataset because both control long-scale image effects. We observe over-aggressive variation in art with changes in noise and weak content control via latent variable edits. Here, we demonstrate that training a modified StyleGAN2, where coarse-scale noise is suppressed, removes these unwanted effects. We obtain a superior FID; changes in noise result in local exploration of style; and identity control is markedly improved. These results and analysis lead towards a GAN-assisted art synthesis tool for digital artists of all skill levels, which can be used in film, games, or any creative industry for artistic ideation.