한국BIM학회 논문집 (Journal of KIBIM)

  • 제12권1호
  • /
  • Pages.55-61
  • /
  • 2022
  • /
  • 2288-1697(pISSN)
  • /
  • 2288-1697(eISSN)
한국BIM학회 (Korean Institute of Building Information Modeling)
권호 표지
DOI QR코드

DOI QR Code

GAN을 활용한 인테리어 스타일 변환 모델에 관한 연구

A study of interior style transformation with GAN model

  • 최준혁 (서울대학교 환경조경학과) ;
  • 이제승 (서울대학교 환경조경학과)
  • 투고 : 2022.01.24
  • 심사 : 2022.03.08
  • 발행 : 2022.03.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Recently, demand for designing own space is increasing as the rapid growth of home furnishing market. However, there is a limitation that it is not easy to compare the style between before construction view and after view. This study aims to translate real image into another style with GAN model learned with interior images. To implement this, first we established style criteria and collected modern, natural, and classic style images, and experimented with ResNet, UNet, Gradient penalty concept to CycleGAN algorithm. As a result of training, model recognize common indoor image elements, such as floor, wall, and furniture, and suitable color, material was converted according to interior style. On the other hand, the form of furniture, ornaments, and detailed pattern expressions are difficult to be recognized by CycleGAN model, and the accuracy lacked. Although UNet converted images more radically than ResNet, it was more stained. The GAN algorithm allowed us to represent results within 2 seconds. Through this, it is possible to quickly and easily visualize and compare the front and after the interior space style to be constructed. Furthermore, this GAN will be available to use in the design rendering include interior.

키워드

과제정보

이 논문은 정부(과학기술정보통신부)의 재원으로 한국연구재단의 지원을 받아 수행된 연구임(No. 2021R1F1A1047492)

참고문헌

  1. Cao, Y., Jia, L., Chen, Y., Lin, N., Yang, C., Zhang, B., Liu, Z., Li, X., Dai, H. (2019). Recent Advances of Generative Adversarial Networks in Computer Vision, IEEE Access, 7, pp. 14985-15006. https://doi.org/10.1109/access.2018.2886814
  2. Choi, Y., Choi, M., Kim, M., Ha, J. W., Kim, S., Choo, J. (2018). Stargan: Unified generative adversarial networks for multi-domain image-to-image translation, In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 8789-8797.
  3. Chung, M. Y., Lee, H. S. (2019). Classification of emotional adjective for the hospital indoor image based on deep learning, Journal of the Korean institute of interior design, 28(6), pp. 75-85. https://doi.org/10.14774/jkiid.2019.28.6.075
  4. Han, S. K., Shin, D. Y. (2021). A study on architectural image generation using artificial intelligence algorithm: A fundamental study on the generation of due diligence images based on architectural sketch, Journal of KIBIM, 11(2), pp. 54-59. https://doi.org/10.13161/KIBIM.2021.11.2.054
  5. Han, S. W., Lee, K. S. (2002). Modeling for estimation of improving indoor environment using interior plants, Journal of the Korean institute of interior landscape architecture, 4(2), pp. 79-89.
  6. Johnson, J., Alahi, A., Fei-Fei, L. (2016). Perceptual losses for real-time style transfer and super-resolution, In European conference on computer vision, pp. 694-711.
  7. Kim, J. S., Lee, J. K. (2020). Implementation and application of interior design style training model using deep learning, Journal of the Korean institute of interior design, 29(5), pp. 96-104. https://doi.org/10.14774/JKIID.2020.29.5.096
  8. Kim, S. K. (2018). A study on the development plan of domestic home furnishing industry, Journal of the Korean furniture society, 29(4), pp. 228-244.
  9. Kim, S. W., Park, K. H. (2018). U-net and Residual-based Cycle-GAN for improving object transfiguration performance, The Journal of Korea Robotics Society, 13(1), pp. 1-7. https://doi.org/10.7746/jkros.2018.13.1.001
  10. Lee, D. J., Ko, E. H. (2011). A study on the relationship between personality and interior style preference, Journal of the architectural institute of Korea planning & design, 27(2), pp. 99-106.
  11. Liu, Y. (2021). Improved generative adversarial network and its application in image oil painting style transfer, Image and Vision Computing, 105, 104087. https://doi.org/10.1016/j.imavis.2020.104087
  12. Min, J. H., Choi, G. S. (2014). Study on color & texture image of finishing material by interior component: centered on interior desing style type, Journal of Korea society of color studies, 28(4), pp. 75-87. https://doi.org/10.17289/jkscs.28.4.201411.75
  13. Sun, T., Jung, C., Fu, Q., Han, Q. (2019). Nir to rgb domain translation using asymmetric cycle generative adversarial networks, IEEE Access, 7, pp. 112459-112469. https://doi.org/10.1109/access.2019.2933671
  14. Ye, X., Du, J., Ye, Y. (2021). MasterplanGAN: Facilitating the sma rt rende r ing of u rban maste r p lans v ia generative adversarial networks, Environment and Planning B: Urban Analytics and City Science, doi: 10.1177/23998083211023516
  15. Zhan, F., Huang, J., Lu, S. (2019). Adaptive composition gan towards realistic image synthesis, arXiv preprint arXiv:1905.04693v1
  16. Zhu, J. Y., Park, T., Isola, P., Efros, A. A. (2017). Unpaired image-to-image translation using cycle-consistent adversarial networks, In Proceedings of the IEEE international conference on computer vision, pp. 2223-2232.