Skip navigation

DSpace

機構典藏 DSpace 系統致力於保存各式數位資料(如:文字、圖片、PDF)並使其易於取用。

點此認識 DSpace
DSpace logo
English
中文
  • 瀏覽論文
    • 校院系所
    • 出版年
    • 作者
    • 標題
    • 關鍵字
    • 指導教授
  • 搜尋 TDR
  • 授權 Q&A
    • 我的頁面
    • 接受 E-mail 通知
    • 編輯個人資料
  1. NTU Theses and Dissertations Repository
  2. 電機資訊學院
  3. 資訊工程學系
請用此 Handle URI 來引用此文件: http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/85718
完整後設資料紀錄
DC 欄位值語言
dc.contributor.advisor李明穗zh_TW
dc.contributor.advisorMing-Sui Leeen
dc.contributor.author簡莘洳zh_TW
dc.contributor.authorHsin-Ju Chienen
dc.date.accessioned2023-03-19T23:22:21Z-
dc.date.available2023-11-09-
dc.date.copyright2023-07-11-
dc.date.issued2022-
dc.date.submitted2002-01-01-
dc.identifier.citation[1] Cyber. Oncyber, 2021.
[2] MomentX-Network. Momentx, 2021.
[3] XRSPACE. Goxr, 2021.
[4] Leon A. Gatys, Alexander S. Ecker, and Matthias Bethge. Image style transfer using convolutional neural networks. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 2414–2423, 2016.
[5] Justin Johnson, Alexandre Alahi, and Li Fei-Fei. Perceptual losses for real-time style transfer and super-resolution. In Bastian Leibe, Jiri Matas, Nicu Sebe, and Max Welling, editors, Computer Vision – ECCV 2016, pages 694 711, Cham, 2016. Springer International Publishing.
[6] Vincent Dumoulin, Jonathon Shlens, and Manjunath Kudlur. A learned representation for artistic style, 2016.
[7] Xun Huang and Serge Belongie. Arbitrary style transfer in real-time with adaptive instance normalization. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), Oct 2017.
[8] Yijun Li, Chen Fang, Jimei Yang, Zhaowen Wang, Xin Lu, and Ming-Hsuan Yang. Universal style transfer via feature transforms. In I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, editors, Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc., 2017.
[9] Dae Young Park and Kwang Hee Lee. Arbitrary style transfer with style attentional networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019.
[10] Songhua Liu, Tianwei Lin, Dongliang He, Fu Li, Meiling Wang, Xin Li, Zhengxing Sun, Qian Li, and Errui Ding. Adaattn: Revisit attention mechanism in arbitrary neural style transfer. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 6649–6658, October 2021.
[11] Haibo Chen, lei zhao, Zhizhong Wang, Huiming Zhang, Zhiwen Zuo, Ailin Li, Wei Xing, and Dongming Lu. Artistic style transfer with internal-external learning and contrastive learning. In M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J. Wortman Vaughan, editors, Advances in Neural Information Processing Systems, volume 34, pages 26561–26573. Curran Associates, Inc., 2021.
[12] Manuel Ruder, Alexey Dosovitskiy, and Thomas Brox. Artistic style transfer for videos. In Bodo Rosenhahn and Bjoern Andres, editors, Pattern Recognition, pages 26–36, Cham, 2016. Springer International Publishing.
[13] Xueting Li, Sifei Liu, Jan Kautz, and Ming-Hsuan Yang. Learning linear transformations for fast image and video style transfer. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019.
[14] Manuel Ruder, Alexey Dosovitskiy, and Thomas Brox. Artistic style transfer for videos. In Bodo Rosenhahn and Bjoern Andres, editors, Pattern Recognition, pages 26–36, Cham, 2016. Springer International Publishing.
[15] Wenjing Wang, Jizheng Xu, Li Zhang, Yue Wang, and Jiaying Liu. Consistent video style transfer via compound regularization. Proceedings of the AAAI Conference on Artificial Intelligence, 34(07):12233–12240, Apr. 2020.
[16] Hiroharu Kato, Yoshitaka Ushiku, and Tatsuya Harada. Neural 3d mesh renderer. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR), June 2018.
[17] Alexander Mordvintsev, Nicola Pezzotti, Ludwig Schubert, and Chris Olah. Differentiable image parameterizations. Distill, 3, 07 2018.
[18] Jhih-Hong Hsu. Style transfer of 3d scenes, 2019.
[19] Mattia Segu, Margarita Grinvald, Roland Siegwart, and Federico Tombari. 3dsnet: Unsupervised shape-to-shape 3d style transfer, 2020.
[20] Kangxue Yin, Jun Gao, Maria Shugrina, Sameh Khamis, and Sanja Fidler. 3dstylenet: Creating 3d shapes with geometric and texture style variations. In Proceedings of International Conference on Computer Vision (ICCV), 2021.
[21] Reinhard Oppermann. User-interface Design, pages 233–248. Springer Berlin Heidelberg, Berlin, Heidelberg, 2002.
[22] John Brooke. Sus: A quick and dirty usability scale, 1996.
-
dc.identifier.urihttp://tdr.lib.ntu.edu.tw/jspui/handle/123456789/85718-
dc.description.abstract近年来,由於疫情的爆發,許多活動都改為線上的方式舉辦以避免疫情擴散,如虛擬藝廊。然而,在目前的虛擬藝廊中,無論是策展人或是觀賞者皆只能對藝術品進行有限的操作,為此我們希望透過風格轉換來讓策展者能夠藉此技術發展更多元的體驗形式,並讓觀賞者透過風格轉換的過程增加對於藝術品的認識,加深與藝術作品的連結。在本篇論文中,我們提出了一個互動式風格轉換虛擬藝廊系統,在系統設計階段,我們比較不同風格轉換方法產生的結果,並根據文中提及的考量因素選擇其中兩種方法整合至我們的系統。接著,使用者可以透過使用者介面對虛擬藝廊中的畫框、卡紙、圖片、以及3D藝術品進行風格轉換。最後,我們進行了一項使用者研究來評估本系統的有效性。结果顯示,在虛擬藝廊中加入風格轉換不只能夠增添虛擬藝廊體驗的豐富性,對於提升藝術品的美感也有一定的幫助,對於觀賞者而言,不僅能在觀賞過程中增添趣味性,更能藉由選擇不同風格的過程,加深對於藝術品的印象。zh_TW
dc.description.abstractIn recent years, due to the outbreak of the epidemic, many events have been held online to avoid spreading illness, such as the virtual gallery. However, in the current virtual galleries, both curators and viewers can only do limited manipulation of the artwork. Therefore, we hope that through style transfer, curators can use this technology to develop more diversified forms of experience, and viewers can increase their understanding of the artworks and deepen their connection with the artworks through the process of style transfer. In this thesis, we propose an interactive style transfer virtual gallery system. In the system design phase, we compare the results of different style transfer methods and select two of them to integrate into our system based on our considerations. Then, users can perform style transfer on pictures, paper jams, frames, and 3D artworks in the virtual gallery through the user interface. Finally, we conducted a user study to evaluate the effectiveness of this system. The results show that adding style transfer to the virtual gallery not only increases the richness of the virtual gallery experience, but also enhances the aesthetics of the artwork. For the viewers, it not only makes the viewing process more interesting, but also deepens the impression of the artwork through the process of choosing different styles.en
dc.description.provenanceMade available in DSpace on 2023-03-19T23:22:21Z (GMT). No. of bitstreams: 1
U0001-1209202218364300.pdf: 14171721 bytes, checksum: 36e71ba083f3195cda10c03f3744f6ec (MD5)
Previous issue date: 2022
en
dc.description.tableofcontents摘要 - i
Abstract - ii
Contents - iv
List of Figures - vi
List of Tables - viii
Chapter 1 Introduction - 1
Chapter 2 Related Work - 3
2.1 Image Style Transfer - 3
2.2 Video Style Transfer - 4
2.3 3D Style Transfer - 5
Chapter 3 System Design and Implementation - 7
3.1 Object Type - 7
3.2 Model Selection - 8
3.2.1 Qualitative Comparison of Stylized 2D Image - 8
3.2.2 Qualitative Comparison of Stylized 3D Object - 11
3.3 Style Selection - 13
3.4 User Interface Design - 14
3.5 Implementation - 16
3.5.1 Virtual Gallery in Desktop - 16
3.5.2 Data Flow - 17
3.5.3 Transferred Results - 17
Chapter 4 System Evaluation - 23
4.1 User Study Design - 23
4.1.1 Scene Setup - 23
4.1.2 Tasks - 23
4.1.3 VR Mode - 25
4.2 Procedure - 25
4.3 Experimental Results - 27
Chapter 5 Discussion - 32
Chapter 6 Conclusion and Future Works - 35
6.1 Conclusion - 35
6.2 Future Work - 35
References - 37
-
dc.language.isoen-
dc.subject虛擬藝廊zh_TW
dc.subject使用者系統互動zh_TW
dc.subject風格轉換zh_TW
dc.subjectStyle Transferen
dc.subjectUser System Interactionen
dc.subjectVirtual Galleryen
dc.title互動式風格轉換在虛擬藝廊的應用zh_TW
dc.titleApplications of Interactive Style Transfer to Virtual Galleryen
dc.typeThesis-
dc.date.schoolyear110-2-
dc.description.degree碩士-
dc.contributor.coadvisor洪一平zh_TW
dc.contributor.coadvisorYi-Ping Hungen
dc.contributor.oralexamcommittee王碩仁zh_TW
dc.contributor.oralexamcommitteeShoue-jen Wangen
dc.subject.keyword風格轉換,虛擬藝廊,使用者系統互動,zh_TW
dc.subject.keywordStyle Transfer,Virtual Gallery,User System Interaction,en
dc.relation.page39-
dc.identifier.doi10.6342/NTU202203319-
dc.rights.note同意授權(全球公開)-
dc.date.accepted2022-09-26-
dc.contributor.author-college電機資訊學院-
dc.contributor.author-dept資訊工程學系-
dc.date.embargo-lift2025-08-01-
顯示於系所單位:資訊工程學系

文件中的檔案:
檔案 大小格式 
U0001-1209202218364300.pdf13.84 MBAdobe PDF檢視/開啟
顯示文件簡單紀錄


系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。

社群連結
聯絡資訊
10617臺北市大安區羅斯福路四段1號
No.1 Sec.4, Roosevelt Rd., Taipei, Taiwan, R.O.C. 106
Tel: (02)33662353
Email: ntuetds@ntu.edu.tw
意見箱
相關連結
館藏目錄
國內圖書館整合查詢 MetaCat
臺大學術典藏 NTU Scholars
臺大圖書館數位典藏館
本站聲明
© NTU Library All Rights Reserved