DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 김문철 | - |
dc.contributor.author | Kim, Taehwan | - |
dc.contributor.author | 김태환 | - |
dc.date.accessioned | 2024-07-30T19:31:49Z | - |
dc.date.available | 2024-07-30T19:31:49Z | - |
dc.date.issued | 2024 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1097280&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/321699 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2024.2,[iv, 37 p. :] | - |
dc.description.abstract | In the industry, to apply image restoration technology that converts low-quality images into high-quality ones, it is necessary to restore images with complex and mixed degradation. However, existing deep learning-based methods have been focused on restoring images with a single type of degradation. In particular, Transformer-based methods for image restoration of single degradation are effective but require a new approach for images with mixed degradation. In this thesis, we propose a model using Transformer-based two-stage U-Nets for image restoration of mixed degradation that is suitable for the real world. The proposed two-stage U-Net Transformer (TUT) effectively restores images with mixed degradation by dividing a complex problem into gray-scale image restoration and color-scale image restoration, thereby outperforming existing Transformer-based image restoration models. In particular, we designed spatial-wise Transformer-based U-Net for gray-scale image restoration and channel-wise Transformer-based U-Net for color-scale image restoration. This approach effectively performed image restoration of mixed degradation. Moreover, to address shortcomings of existing Transformer-based models and maximize performance, we introduced spatial-wise and channel-wise modulators. Additionally, various loss functions were used to optimize image restoration of mixed degradation. Lastly, we proposed synthetic data pre-processing techniques capable of representing both spatial and color degradation. This approach enabled more detailed representations of real-world degradation compared to an existing synthetic degradation dataset. Experimental results showed that the proposed TUT outperformed existing Transformer-based image restoration models on various evaluation datasets. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 영상 복원▼a혼합 열화▼a트랜스포머▼a컴퓨터 비전▼a딥러닝 | - |
dc.subject | Image restoration▼aMixed degradation▼aTransformer▼aComputer vision▼aDeep learning | - |
dc.title | Image restoration of mixed degradation using transformer-based two-stage U-Nets | - |
dc.title.alternative | 트랜스포머 기반 2단계 U-Net을 이용한 혼합 열화 영상 복원 연구 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | Kim, Munchurl | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.