DeepPixelMonster_super_final
- 1. Deep Convolutional Generative Adversarial Networks (DCGANs) for Creating Pixel Art Lawrence Du
- 2. Creating art for mobile apps takes skill and money
- 3. Problem: The Costs of Making Art for Indie/Mobile Games Total cost of adding one new character: $109,000 Artwork cost: $30,000
- 4. Problem: The Costs of Making Art for Indie/Mobile Games Total cost of adding one new character: $109,000 Artwork cost: $30,000
- 5. Deep Learning for AI assisted art generation Fake pictures of bedrooms created by deep neural network
- 6. One franchise built around pixel art... Pokémon Red (released 1998)
- 7. Using Pokémon as a training set ● 64 x 64 x 3 pixels = 12,228 features per image ● 700+ Unique Pokémon ● 76,000+ animation frames
- 8. Feature engineering with images ● database used for eliminating shape outliers ● 231 Pokémon selected (19,231 frames) ● Expansion of training set size: ○ Brightness ○ Hue ○ Contrast ○ Left-right transformations.
- 9. Feature engineering with images ● database used for eliminating outliers ● 231 Pokémon selected (19,231 frames) ● Expansion of training set size: ○ Brightness ○ Hue ○ Contrast ○ Left-right transformations.
- 10. Feature engineering with images ● database used for eliminating outliers ● 231 Pokémon selected (19,231 frames) ● Expansion of training set size: ○ Brightness ○ Hue ○ Contrast ○ Left-right transformations.
- 12. Implementation ● Written using ● 30+ neural architecture combinations tested. ● Training takes 20-30 minutes on GPU ● Front-end Python ● Amazon AWS
- 17. ● LINE messenger - $238 million on stickers in 2015 ● Easier to send a sticker than to write Chinese characters (kanji) Additional use cases for AI pixel art
- 18. Lawrence Du larrydu88@gmail.com PhD Biological Sciences (UC San Diego)
- 19. Solution: Use Deep Learning for AI assisted art generation AI generated music album covers