Journal of Korea Game Society (한국게임학회 논문지)

Korea Game Society (한국게임학회)
권호 표지
DOI QR코드

DOI QR Code

2D Game Image Color Synthesis System Using Convolutional Neural Network

컨볼루션 인공신경망을 이용한 2차원 게임 이미지 색상 합성 시스템

  • 홍승진 (홍익대학교 일반대학원 게임학과(공학)) ;
  • 강신진 (홍익대학교 일반대학원 게임학과(공학)) ;
  • 조성현 (홍익대학교 일반대학원 게임학과(공학))
  • Received : 2018.03.16
  • Accepted : 2018.04.20
  • Published : 2018.04.20
Download PDF
⟨ Previous Next ⟩

Abstract

The recent Neural Network technique has shown good performance in content generation such as image generation in addition to the conventional classification problem and clustering problem solving. In this study, we propose an image generation method using artificial neural network as a next generation content creation technique. The proposed artificial neural network model receives two images and combines them into a new image by taking color from one image and shape from the other image. This model is made up of Convolutional Neural Network, which has two encoders for extracting color and shape from images, and a decoder for taking all the values of each encoder and generating a combination image. The result of this work can be applied to various 2D image generation and modification works in game development process at low cost.

최근의 인공 신경망(Neural Network) 기법은 전통적인 분류 문제와 군집화 문제 해결에서 벗어나 이미지 생성 같은 컨텐츠 생성에서도 좋은 성능을 보이고 있다. 본 연구에서는 차세대 컨텐츠 생성 기법으로 인공신경망을 이용한 이미지 생성기법을 제안한다. 제안하는 인공신경망 모델은 두개의 이미지를 입력받아서 하나의 이미지에서는 색상을, 다른 이미지에서는 모양을 가져와 새로운 이미지로 조합해낸다. 이 모델은 컨볼루션 인공신경망(Convolutional Neural Network)으로 제작되었으며 각각 이미지에서 색상과 모양을 추출해내는 두 개의 인코더와 각 인코더의 값을 모두 넘겨받아 하나의 조합이 되는 이미지를 생성해내는 하나의 디코더로 구성이 되어있다. 본 연구의 성과는 저비용으로 게임 개발 프로세스 상 다양한 2차원 이미지 생성 및 보정 작업에 활용될 수 있다.

Keywords

References

  1. Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. "Imagenet classification with deep convolutional neural networks." Advances in neural information processing systems, pp1097-1105, 2012.
  2. Mikolov, Tomáš, et al. "Recurrent neural network based language model." Eleventh Annual Conference of the International Speech Communication Association, 2010.
  3. Hochreiter, Sepp, and Jürgen Schmidhuber. "Long short-term memory." Neural computation 9.8, pp.1735-1780, 1997. https://doi.org/10.1162/neco.1997.9.8.1735
  4. Dauphin, Y., de Vries, H., & Bengio, Y. Equilibrated adaptive learning rates for non-convex optimization. In Advances in neural information processing systems, pp. 1504-1512, 2015.
  5. Gatys, Leon A., Alexander S. Ecker, and Matthias Bethge. "A neural algorithm of artistic style." arXiv preprint arXiv:1508.06576, 2015
  6. Goodfellow, Ian, et al. "Generative adversarial nets." Advances in neural information processing systems, pp.2672-2680, 2014.
  7. Dosovitskiy, A., Springenberg, J. T., & Brox, T. (2015, June). Learning to generate chairs with convolutional neural networks. In Computer Vision and Pattern Recognition (CVPR), IEEE Conference on pp.1538-1546, 2015.
  8. Hinton, Geoffrey E., and Ruslan R. Salakhutdinov. "Reducing the dimensionality of data with neural networks." science 313.5786, pp.504-507, 2006. https://doi.org/10.1126/science.1127647
  9. Jain, Rishabh, et al. "Autoencoders for level generation, repair, and recognition." Proceedings of the ICCC Workshop on Computational Creativity and Games, 2016.
  10. Xue, Tianfan, et al. "Visual dynamics: Probabilistic future frame synthesis via cross convolutional networks." Advances in Neural Information Processing Systems, pp.91-99, 2016.
  11. Reed, Scott E., et al. "Deep visual analogy-making." Advances in neural information processing systems, pp.1252-1260, 2015.