Application of Variational AutoEncoder (VAE) Model and Image Processing Approaches in Game Design
In recent decades, the Variational AutoEncoder (VAE) model has shown good potential and capability in image generation and dimensionality reduction. The combination of VAE and various machine learning frameworks has also worked effectively in different daily life applications, however its possible u...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/7/3457 |
| _version_ | 1797607051641225216 |
|---|---|
| author | Hugo Wai Leung Mak Runze Han Hoover H. F. Yin |
| author_facet | Hugo Wai Leung Mak Runze Han Hoover H. F. Yin |
| author_sort | Hugo Wai Leung Mak |
| collection | DOAJ |
| description | In recent decades, the Variational AutoEncoder (VAE) model has shown good potential and capability in image generation and dimensionality reduction. The combination of VAE and various machine learning frameworks has also worked effectively in different daily life applications, however its possible use and effectiveness in modern game design has seldom been explored nor assessed. The use of its feature extractor for data clustering has also been minimally discussed in the literature neither. This study first attempts to explore different mathematical properties of the VAE model, in particular, the theoretical framework of the encoding and decoding processes, the possible achievable lower bound and loss functions of different applications; then applies the established VAE model to generate new game levels based on two well-known game settings; and to validate the effectiveness of its data clustering mechanism with the aid of the Modified National Institute of Standards and Technology (MNIST) database. Respective statistical metrics and assessments are also utilized to evaluate the performance of the proposed VAE model in aforementioned case studies. Based on the statistical and graphical results, several potential deficiencies, for example, difficulties in handling high-dimensional and vast datasets, as well as insufficient clarity of outputs are discussed; then measures of future enhancement, such as tokenization and the combination of VAE and GAN models, are also outlined. Hopefully, this can ultimately maximize the strengths and advantages of VAE for future game design tasks and relevant industrial missions. |
| first_indexed | 2024-03-11T05:25:53Z |
| format | Article |
| id | doaj.art-78d5b742528c46eca59f23a7ec946566 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T05:25:53Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-78d5b742528c46eca59f23a7ec9465662023-11-17T17:32:49ZengMDPI AGSensors1424-82202023-03-01237345710.3390/s23073457Application of Variational AutoEncoder (VAE) Model and Image Processing Approaches in Game DesignHugo Wai Leung Mak0Runze Han1Hoover H. F. Yin2Department of Mathematics, The Chinese University of Hong Kong, Shatin, New Territories, Hong Kong, ChinaDepartment of Mathematics, The Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong, ChinaDepartment of Information Engineering, The Chinese University of Hong Kong, Shatin, New Territories, Hong Kong, ChinaIn recent decades, the Variational AutoEncoder (VAE) model has shown good potential and capability in image generation and dimensionality reduction. The combination of VAE and various machine learning frameworks has also worked effectively in different daily life applications, however its possible use and effectiveness in modern game design has seldom been explored nor assessed. The use of its feature extractor for data clustering has also been minimally discussed in the literature neither. This study first attempts to explore different mathematical properties of the VAE model, in particular, the theoretical framework of the encoding and decoding processes, the possible achievable lower bound and loss functions of different applications; then applies the established VAE model to generate new game levels based on two well-known game settings; and to validate the effectiveness of its data clustering mechanism with the aid of the Modified National Institute of Standards and Technology (MNIST) database. Respective statistical metrics and assessments are also utilized to evaluate the performance of the proposed VAE model in aforementioned case studies. Based on the statistical and graphical results, several potential deficiencies, for example, difficulties in handling high-dimensional and vast datasets, as well as insufficient clarity of outputs are discussed; then measures of future enhancement, such as tokenization and the combination of VAE and GAN models, are also outlined. Hopefully, this can ultimately maximize the strengths and advantages of VAE for future game design tasks and relevant industrial missions.https://www.mdpi.com/1424-8220/23/7/3457game designvariational autoencoder (VAE)image and video generationBayesian algorithmloss functiondata clustering |
| spellingShingle | Hugo Wai Leung Mak Runze Han Hoover H. F. Yin Application of Variational AutoEncoder (VAE) Model and Image Processing Approaches in Game Design Sensors game design variational autoencoder (VAE) image and video generation Bayesian algorithm loss function data clustering |
| title | Application of Variational AutoEncoder (VAE) Model and Image Processing Approaches in Game Design |
| title_full | Application of Variational AutoEncoder (VAE) Model and Image Processing Approaches in Game Design |
| title_fullStr | Application of Variational AutoEncoder (VAE) Model and Image Processing Approaches in Game Design |
| title_full_unstemmed | Application of Variational AutoEncoder (VAE) Model and Image Processing Approaches in Game Design |
| title_short | Application of Variational AutoEncoder (VAE) Model and Image Processing Approaches in Game Design |
| title_sort | application of variational autoencoder vae model and image processing approaches in game design |
| topic | game design variational autoencoder (VAE) image and video generation Bayesian algorithm loss function data clustering |
| url | https://www.mdpi.com/1424-8220/23/7/3457 |
| work_keys_str_mv | AT hugowaileungmak applicationofvariationalautoencodervaemodelandimageprocessingapproachesingamedesign AT runzehan applicationofvariationalautoencodervaemodelandimageprocessingapproachesingamedesign AT hooverhfyin applicationofvariationalautoencodervaemodelandimageprocessingapproachesingamedesign |