GAN을 활용한 인테리어 스타일 변환 모델에 관한 연구

• 영문명: A study of interior style transformation with GAN model
• 발행기관: 한국BIM학회
• 저자명: 최준혁(Choi, Jun-Hyeck) 이제승(Lee, Jae-Seung)
• 간행물 정보: 『KIBIM Magazine』KIBIM Magazine 12권 1호, 55~61쪽, 전체 7쪽
• 주제분류: 공학 > 건축공학
• 파일형태: PDF
• 발행일자: 2022.03.30

영문 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.

목차

1. 서론

2. 기존 관련 연구 고찰

3. 이미지 데이터 구축과 CycleGAN 제작

4. 이미지 학습 및 결과

5. 결론 및 제언

감사의 글

References

키워드

CycleGAN 이미지 변환 인테리어 스타일 이미지 렌더링 CycleGAN Image Translation Interior Style Image Rendering