Towards Generating Image Assets Through Deep Learning for Game Development

Tilson, Adam; Gelowitz, Craig M.

doi:10.1109/ccece.2019.8861965

Cited by 6 publications

(5 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, VAE-GAN technology has been used to develop adaptive difficulty levels and game narratives that change based on the player's style and progress, which keeps the gameplay engaging and challenging [6]. Furthermore, by automating part of the content creation process, VAE-GANs reduce the workload on game developers, enabling them to focus on more creative aspects of game design [26]. This technology enhances player engagement and streamlines the development process, allowing for the quicker release of more complex games.…”

Section: Video Game Developmentmentioning

confidence: 99%

Enhancing capabilities of generative models through VAE-GAN integration: A review

Cai

2024

ACE

View full text Add to dashboard Cite

Our review explores the integration of Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs), which are pivotal in the realm of generative models. VAEs are renowned for their robust probabilistic foundations and capacity for complex data representation learning, while GANs are celebrated for generating high-fidelity images. Despite their strengths, both models have limitations: VAEs often produce less sharp outputs, and GANs face challenges with training stability. The hybrid VAE-GAN models harness the strengths of both architectures to overcome these limitations, enhancing output quality and diversity. We provide a comprehensive overview of VAEs and GANs technology developments, their integration strategies, and resultant performance improvements. Applications across various fields, such as artistic creation, medical imaging, e-commerce, and video gaming, highlight the transformative potential of these models. However, challenges in model robustness, ethical concerns, and computational demands persist, posing significant hurdles. Future research directions are poised to transform the VAE-GAN landscape significantly. Enhancing training stability remains a priority, with new approaches such as incorporating self-correcting mechanisms into GANs training being tested. Addressing ethical issues is also critical, as policymakers and technologists work together to develop standards that prevent misuse. Moreover, reducing computational costs is fundamental to democratizing access to these technologies. Projects such as the development of MobileNetV2 have made strides in creating more efficient neural network architectures that maintain performance while being less resource-intensive. Further, the exploration of VAE-GAN applications in fields like augmented reality and personalized medicine offers exciting opportunities for growth, as evidenced by recent pilot studies.

show abstract

Section: Video Game Developmentmentioning

confidence: 99%

Enhancing capabilities of generative models through VAE-GAN integration: A review

Cai

2024

ACE

View full text Add to dashboard Cite

show abstract

“…In addition, Green et al (2021) proposed a framework generating tutorial text by discovering whether it is effective to win or lose a game. Tilson and Gelowitz (2019) investigated generating image assets for games using unsupervised learning such as GAN and VAE. Volz et al (2018) have generated various levels of Super Mario Bros. using GAN.…”

Section: Business Feedbackmentioning

confidence: 99%

GenéLive! Generating Rhythm Actions in Love Live!

Takada¹,

Yamazaki²,

Yoshida³

et al. 2023

AAAI

View full text Add to dashboard Cite

This article presents our generative model for rhythm action games together with applications in business operation. Rhythm action games are video games in which the player is challenged to issue commands at the right timings during a music session. The timings are rendered in the chart, which consists of visual symbols, called notes, flying through the screen. We introduce our deep generative model, GenéLive!, which outperforms the state-of-the-art model by taking into account musical structures through beats and temporal scales. Thanks to its favorable performance, GenéLive! was put into operation at KLab Inc., a Japan-based video game developer, and reduced the business cost of chart generation by as much as half. The application target included the phenomenal "Love Live!", which has more than 10 million users across Asia and beyond, and is one of the few rhythm action franchises that has led the online era of the genre. In this article, we evaluate the generative performance of GenéLive! using production datasets at KLab as well as open datasets for reproducibility, while the model continues to operate in their business. Our code and the model, tuned and trained using a supercomputer, are publicly available.

show abstract

“…One of the most explored creative fields by AI researchers is (video)game design. With respect to GDL, it typically concerns the use of generated images (Tilson and Gelowitz, 2019), characters (Jin et al, 2017), or soundtracks 10 inside games; in these cases, all the conclusions drawn until now are still valid, and no additional considerations are required. However, a growing application is the so-called procedural content generation, where the game scenarios are dynamically generated during game (Liu et al, 2021).…”

Section: Policy Suggestionsmentioning

confidence: 99%

Copyright in generative deep learning

Giorgio

Musolesi

2022

Data & Policy

View full text Add to dashboard Cite

Machine-generated artworks are now part of the contemporary art scene: they are attracting significant investments and they are presented in exhibitions together with those created by human artists. These artworks are mainly based on generative deep learning (GDL) techniques, which have seen a formidable development and remarkable refinement in the very recent years. Given the inherent characteristics of these techniques, a series of novel legal problems arise. In this article, we consider a set of key questions in the area of GDL for the arts, including the following: is it possible to use copyrighted works as training set for generative models? How do we legally store their copies in order to perform the training process? Who (if someone) will own the copyright on the generated data? We try to answer these questions considering the law in force in both the United States and the European Union, and potential future alternatives. We then extend our analysis to code generation, which is an emerging area of GDL. Finally, we also formulate a set of practical guidelines for artists and developers working on deep learning generated art, as well as some policy suggestions for policymakers.

show abstract

Towards Generating Image Assets Through Deep Learning for Game Development

Cited by 6 publications

References 2 publications

Enhancing capabilities of generative models through VAE-GAN integration: A review

Enhancing capabilities of generative models through VAE-GAN integration: A review

GenéLive! Generating Rhythm Actions in Love Live!

Copyright in generative deep learning

Contact Info

Product

Resources

About