Disclaimer: This essay is provided as an example of work produced by students studying towards a computer science degree, it is not illustrative of the work produced by our in-house experts. Click here for sample essays written by our professional writers.

Any opinions, findings, conclusions or recommendations expressed in this material are those of the authors and do not necessarily reflect the views of UKEssays.com.

Wave Function Collapse in Deep Convolutional Generative Adversarial Network

Paper Type: Free Essay Subject: Computer Science
Wordcount: 6110 words Published: 18 May 2020

Reference this

 

  1. Abstract

The procedural content generation algorithms are a well-known concept in the game industry. Because of their time efficiency, there is more effort put into developing new algorithms. The Wave Function Collapse algorithm developed by Max Gumin is populating the pattern from a small sample. The algorithm gained much popularity because of the variety of the outputs generated from only one input. This paper examines whether the wave function collapse can be trained within a use of Deep Convolutional Generative Adversarial Network to get the output starting with the input specified by the user. This would give additional control over the algorithm and allow to specify the spatial distribution of tiles across the solution space.

Keywords: Wave Function Collapse, Procedural City Generation, Machine Learning, Generative Adversarial Network

Table of contents

Abstract

Acknowledgement

1. Introduction

1.1 The aim of the project

1.2 The structure of the document

1. Background

2.1 Wave Function Collapse

2.2 Artificial Intelligence application to Wave Function Collapse

2.3 Algorithmic Complexity

2. Approach 1: Generative Adversarial Networks

2.1. Introduction

2.2. Dataset preparation

2.3. Image encoding

2.4. Image-to-image translation

2.5. Image post-processing

2.6. Evaluation of results

3. Approach 2: Modification of probability and entropy

3.1. Introduction

3.2. Input image

3.3. Result measurement

3.3.1. Linear mapping based on the lowest and the highest weight

3.3.1. Exponential growth

3.3.2. Enforcing the patterns building desirable content

3.4. Entropy

4. Results

5. Conclusion

6. Appendices

7. References

List of figures

Figure 1 Something something

Figure 2 On the left: Input image that indicates areas with specific desirable values, on the right: the solution that corresponds to the input image

Figure 3 Examples of the 2D patterns generated by Max Gumin with a use of WFC

Figure 4 Island generated with Wave Function Collapse in Bad North

Cite This Work

To export a reference to this article please select a referencing stye below:

Reference Copied to Clipboard.
Reference Copied to Clipboard.
Reference Copied to Clipboard.
Reference Copied to Clipboard.
Reference Copied to Clipboard.
Reference Copied to Clipboard.
Reference Copied to Clipboard.

Related Services

View all

DMCA / Removal Request

If you are the original writer of this essay and no longer wish to have your work published on UKEssays.com then please click the following link to email our support team:

Request essay removal

Related Services

Our academic writing and marking services can help you!

Prices from

£99

Approximate costs for:

  • Undergraduate 2:2
  • 1000 words
  • 7 day delivery

Order an Essay

Related Lectures

Study for free with our range of university lecture notes!

Academic Knowledge Logo

Freelance Writing Jobs

Looking for a flexible role?
Do you have a 2:1 degree or higher?

Apply Today!