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/123456789/74059
完整後設資料紀錄
DC 欄位值語言
dc.contributor.advisor洪一平
dc.contributor.authorJhih-Hong Hsuen
dc.contributor.author徐誌鴻zh_TW
dc.date.accessioned2021-06-17T08:18:24Z-
dc.date.available2024-08-18
dc.date.copyright2019-08-18
dc.date.issued2019
dc.date.submitted2019-08-14
dc.identifier.citation[1] Prisma Labs. “Prisma.” 2016. https://prisma-ai.com/
[2] SergeyMorugin. “Ostagram.” 2016. https://www.ostagram.me/
[3] Kato, Hiroharu, Yoshitaka Ushiku, and Tatsuya Harada. 'Neural 3d mesh renderer.' Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018.
[4] Nguyen, Chuong H., et al. '3D material style transfer.' Computer Graphics Forum. Vol. 31. No. 2pt2. Oxford, UK: Blackwell Publishing Ltd, 2012.
[5] Kyprianidis, Jan Eric, et al. 'State of the “Art”: A Taxonomy of Artistic Stylization Techniques for Images and Video.' IEEE transactions on visualization and computer graphics 19.5 (2012): 866-885.
[6] Gatys, Leon A., Alexander S. Ecker, and Matthias Bethge. 'Image style transfer using convolutional neural networks.' Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
[7] Li, Chuan, and Michael Wand. 'Combining markov random fields and convolutional neural networks for image synthesis.' Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016.
[8] Johnson, Justin, Alexandre Alahi, and Li Fei-Fei. 'Perceptual losses for real-time style transfer and super-resolution.' European conference on computer vision. Springer, Cham, 2016.
[9] Dumoulin, Vincent, Jonathon Shlens, and Manjunath Kudlur. 'A learned representation for artistic style.' arXiv preprint arXiv:1610.07629 (2016).
[10] Chen, Tian Qi, and Mark Schmidt. 'Fast patch-based style transfer of arbitrary style.' arXiv preprint arXiv:1612.04337 (2016).
[11] Anjyo, Ken-ichi, and Katsuaki Hiramitsu. 'Stylized highlights for cartoon rendering and animation.' IEEE Computer Graphics and Applications 23.4 (2003): 54-61.
[12] Barla, Pascal, Joëlle Thollot, and Lee Markosian. 'X-toon: an extended toon shader.' Proceedings of the 4th international symposium on Non-photorealistic animation and rendering. ACM, 2006.
[13] Lee, Hyunjun, Sungtae Kwon, and Seungyong Lee. 'Real-time pencil rendering.' Proceedings of the 4th international symposium on Non-photorealistic animation and rendering. ACM, 2006.
[14] Anish Athalye. 'Neural Style.' 2015. https://github.com/anishathalye/neural-style. commit cbf6a64.
[15] Gatys, Leon A., et al. 'Preserving color in neural artistic style transfer.' arXiv preprint arXiv:1606.05897 (2016).
[16] Ronneberger, Olaf, Philipp Fischer, and Thomas Brox. 'U-net: Convolutional networks for biomedical image segmentation.' International Conference on Medical image computing and computer-assisted intervention. Springer, Cham, 2015.
[17] Deschaintre, Valentin, et al. 'Single-image svbrdf capture with a rendering-aware deep network.' ACM Transactions on Graphics (TOG) 37.4 (2018): 128.
[18] Dmitriev, Kirill, and Evgeny Makarov. 'Generating displacement from normal map for use in 3D games.' ACM SIGGRAPH 2011 Talks. ACM, 2011.
[19] In-ting Ran. The Happiness of Farmers. 1967. http://taga-artchive.org
dc.identifier.urihttp://tdr.lib.ntu.edu.tw/jspui/handle/123456789/74059-
dc.description.abstract風格轉換是計算機科學中的熱門話題,有很多研究試圖將圖片轉換為給定的風格,此外產業界也有一些相關的應用與服務。隨著頭戴式顯示器的發展,3D多媒體內容的製作需求增加,例如遊戲和虛擬實境的應用程式。由於製作特定風格的場景是件費時費工的事,所以我們將風格轉換加入到內容製作的流程中。然而,這些研究大部分都專注在2D圖片上,因此我們修改這些方法來達成我們的目標。
在這篇論文中,我們提出了一個將3D場景轉換為繪畫風格的方法。在前處理時,我們轉換表面色彩貼圖的風格,並根據轉換過的貼圖生成法向量貼圖和位移貼圖。在場景實際運行時,我們調整光影效果及添加輪廓來增進轉換的效果。最後,我們展示使用不同部分的風格圖片來進行轉換的效果,並探討執行時的效能。
zh_TW
dc.description.abstractStyle transfer is a popular topic in computer science. There are lots of works try to turn an image into the desired style. In addition, there are some popular commercial products. With the growth of head-mounted display, the demand of 3D multimedia content is increasing, such as games and virtual reality applications. Due to creating a scene in a particular style is time-consuming, we take style transfer into the design process. However, most of these works focus on 2D images. We modify these methods to reach our goal.
In this thesis, we propose a method to transfer the 3D scene style by a specific painting. In the preprocessing stage, we transfer the style of albedo maps. We also generate normal maps and displacement maps according to the transferred albedo maps. In the runtime, we tune the lighting effect and add silhouette to improve the transferred result. Finally, we demonstrate the result of transferring objects by different areas of the style image and discuss the runtime performance.
en
dc.description.provenanceMade available in DSpace on 2021-06-17T08:18:24Z (GMT). No. of bitstreams: 1
ntu-108-R06922049-1.pdf: 8479119 bytes, checksum: 66fe7f0e8ea93827d1ebf421fbe61b3a (MD5)
Previous issue date: 2019
en
dc.description.tableofcontents口試委員會審定書 #
誌謝 i
中文摘要 ii
ABSTRACT iii
CONTENTS iv
LIST OF FIGURES vi
Chapter 1 Introduction 1
Chapter 2 Related Work 3
2.1 Non-Photorealistic Rendering 3
2.2 Style Transfer for 2D Images 3
2.3 Style Transfer for 3D Objects 4
Chapter 3 Style Transfer of 3D Scenes 5
3.1 Textures Generation 5
3.1.1 Albedo Maps 5
3.1.2 Normal Maps 11
3.1.3 Displacement Maps 11
3.2 Shading 14
3.2.1 Lighting and Shadow 14
3.2.2 Silhouette 17
Chapter 4 Results and Discussion 19
4.1 Results of Different Styles 20
4.2 Results Transferred by Different Areas of A Style Image 23
4.3 Performance 25
Chapter 5 Conclusion 26
Chapter 6 Future Work 27
REFERENCES 28
dc.language.isoen
dc.subject3D場景zh_TW
dc.subject風格轉換zh_TW
dc.subject頭戴式顯示器zh_TW
dc.subject虛擬實境zh_TW
dc.subjectstyle transferen
dc.subject3D sceneen
dc.subjecthead-mounted displayen
dc.subjectvirtual realityen
dc.title3D場景之風格轉換zh_TW
dc.titleStyle Transfer of 3D Scenesen
dc.typeThesis
dc.date.schoolyear107-2
dc.description.degree碩士
dc.contributor.oralexamcommittee莊永裕,詹力韋,林經堯
dc.subject.keyword風格轉換,3D場景,頭戴式顯示器,虛擬實境,zh_TW
dc.subject.keywordstyle transfer,3D scene,head-mounted display,virtual reality,en
dc.relation.page29
dc.identifier.doi10.6342/NTU201903212
dc.rights.note有償授權
dc.date.accepted2019-08-14
dc.contributor.author-college電機資訊學院zh_TW
dc.contributor.author-dept資訊工程學研究所zh_TW
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 
ntu-108-1.pdf
  未授權公開取用
8.28 MBAdobe PDF
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