erniechiew commited on
Commit
11e01aa
1 Parent(s): f3035be

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -2
README.md CHANGED
@@ -1,12 +1,24 @@
 
 
 
 
 
 
 
 
1
  # MarioVGG
2
 
3
  **Video Game Generation: A Practical Study using Mario**
4
 
5
  Virtuals Protocol
6
 
 
 
 
 
7
  ## Abstract
8
 
9
- This work reports the study of video generative models for interactive video game generation and simulation. We discuss and explore the use of available pre-trained open-sourced video generation models to create playable interactive video games. While being able to generate short clips of broad range of described scenes, such models still lack controllability and continuity. Given these limitations, we focus on producing and demonstrating a reliable and controllable video game generator on a single game domain. We present **MarioVGG**, a text-to-video diffusion model for controllable video generation on the Super Mario Bros game. **MarioVGG** demonstrates the ability to continously generate consistent and meaningful scenes and levels, as well as simulate the physics and movements of a controllable player all through video.
10
 
11
  ## BibTex
12
 
@@ -18,4 +30,3 @@ This work reports the study of video generative models for interactive video gam
18
  url={https://github.com/Virtual-Protocol/mario-videogamegen/blob/main/static/pdfs/VideoGameGen.pdf},
19
  year={2024}
20
  }
21
- ```
 
1
+ ---
2
+ language:
3
+ - en
4
+ tags:
5
+ - gaming
6
+ - generative ai
7
+ - video generation
8
+ ---
9
  # MarioVGG
10
 
11
  **Video Game Generation: A Practical Study using Mario**
12
 
13
  Virtuals Protocol
14
 
15
+
16
+ <img src="images/MarioVGG_overview.png" alt="MarioVGG Overview" width="1200"/>
17
+
18
+
19
  ## Abstract
20
 
21
+ This work reports the study of video generative models for interactive video game generation and simulation. We discuss and explore the use of available pre-trained open-sourced video generation models to create playable interactive video games. While being able to generate short clips of broad range of described scenes, such models still lack controllability and continuity. Given these limitations, we focus on producing and demonstrating a reliable and controllable video game generator on a single game domain. We present **MarioVGG**, a text-to-video diffusion model for controllable video generation on the Super Mario Bros game. **MarioVGG** demonstrates the ability to continuously generate consistent and meaningful scenes and levels, as well as simulate the physics and movements of a controllable player all through video.
22
 
23
  ## BibTex
24
 
 
30
  url={https://github.com/Virtual-Protocol/mario-videogamegen/blob/main/static/pdfs/VideoGameGen.pdf},
31
  year={2024}
32
  }