學術產出-Theses
Article View/Open
Publication Export
-
題名 基於日本二維動畫風格的三轉二動畫塗抹特效技術
Three to Two Dimensional Smear Effect Technique Based on Two Dimensional Japanese Animation Style作者 林書廷
Lin, Shu-Ting貢獻者 紀明德
Chi, Ming-Te
林書廷
Lin, Shu-Ting關鍵詞 幾何形變
邊緣成像
骨骼動畫
Geometric Deformation
Edge Rendering
Skeletal Animation日期 2023 上傳時間 9-Mar-2023 18:37:28 (UTC+8) 摘要 日本的動畫產業，尤其在亞洲地區，發展至今已成為一門廣為人知的產業，也不斷地產生出許多世界級的作品，在以往傳統製作方式中，總會需要畫師耗費大量工時進行作畫才能製作出一款動畫，而隨時著間推進，有越來越多的數位輔助軟體被整合進製作流程中，試圖加速製作進度以及為畫面添加更多特色。在近期，開始有動畫製作公司採用三維建模的方式來製作動畫，也開始有些動畫作品中的角色直接使用全三維建模的方式製作，但有別於傳統的二維作畫，全三維製作的角色在激烈打鬥或運動的場景中，除了在風格上與二維作畫有所差距，也無法很好地表現出二維作畫中的速度與力道感，導致一般觀眾在觀看上時不時的出現難以言喻的違和感。本研究認為現今三維建模出來的角色在激烈運動時所造成的違和感，其原因為缺少了二維畫師在作畫時常會使用到的塗抹特效技術，因此我們透過幾何形變、邊緣成像，以及骨骼動畫的技術，讓這種日式動畫中的二維作畫特效也可以透過三維的方式成像出來。
The anime industry in Japan, especially in Asia, has developed into a well-known industry and has continuously produced many world-class works. In traditional production methods, animators would spend a lot of time drawing to create an animation, but with the advancements, more and more digital assistance software is integrated into the production process to try and speed up the production and add more features to the scene.Recently, some animation production companies have started using 3D modeling to create animations, and some animation works have characters that are directly made using full 3D modeling. However, unlike traditional 2D animations, the full 3D characters in intense fight or action scenes not only differ in style from 2D animations, but also cannot effectively convey the speed and force feeling in 2D animations, leading to an indescribable sense of discomfort among the general audience when watching.This research considers that the sense of discomfort caused by the intense motion of 3D-modeled characters today is due to the lack of smearing effect techniques that 2D animators often use when drawing. Therefore, through geometric deformation, edge rendering, and skeleton animation techniques, we can also display the 2D animation effects in Japanese animation in a 3D way.參考文獻 [1] Vielman, P., & Akleman, E. (2021). Animated Futurist Sculpting as Dynamic Implicit Shapes. In ACM SIGGRAPH 2021 Posters (pp. 1-2).[2] Cabral, B., & Leedom, L. C. (1993, September). Imaging vector fields using line integral convolution. In Proceedings of the 20th annual conference on Computer graphics and interactive techniques (pp. 263-270).[3] Motomura, J. C. (2015). GuiltyGearXrd’s Art Style: The X Factor Between 2D and 3D. Lecture at GDC.[4] Haller, M., Hanl, C., & Diephuis, J. (2004). Non-photorealistic rendering techniques for motion in computer games. Computers in Entertainment (CIE), 2(4), 11-11.[5] Barla, P., Thollot, J., & Markosian, L. (2006, June). X-toon: An extended toon shader. In Proceedings of the 4th international symposium on Non-photorealistic animation and rendering (pp. 127-132).[6] Petikam, L., Anjyo, K., & Rhee, T. (2021). Shading rig: Dynamic art-directable stylised shading for 3D characters. ACM Transactions on Graphics (TOG), 40(5), 1-14.[7] Schroeder, D., Coffey, D., & Keefe, D. (2010, June). Drawing with the flow: A sketch-based interface for illustrative visualization of 2D vector fields. In Proceedings of the Seventh Sketch-Based Interfaces and Modeling Symposium (pp. 49-56).[8] Bao, W., Lai, W. S., Ma, C., Zhang, X., Gao, Z., & Yang, M. H. (2019). Depth-aware video frame interpolation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 3703-3712).[9] Wang, X., & Yu, J. (2020). Learning to cartoonize using white-box cartoon representations. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 8090-8099).[10] Zheng, Q., Li, Z., & Bargteil, A. (2020). Learning to shadow hand-drawn sketches. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 7436-7445).[11] Perlin, K. (2002, July). Improving noise. In Proceedings of the 29th annual conference on Computer graphics and interactive techniques (pp. 681-682).[12] Igarashi, T., & Igarashi, Y. (2009). Implementing as-rigid-as-possible shape manipulation and surface flattening. journal of graphics, gpu, and game tools, 14(1), 17-30.[13] Hsu, S. C., Lee, I. H., & Wiseman, N. E. (1993, December). Skeletal strokes. In Proceedings of the 6th annual ACM symposium on User interface software and technology (pp. 197-206).[14] Zhang, J. E., Bang, S., Levin, D. I., & Jacobson, A. (2020). Complementary dynamics. arXiv preprint arXiv:2009.02462.[15] Rohmer, D., Tarini, M., Kalyanasundaram, N., Moshfeghifar, F., Cani, M. P., & Zordan, V. (2021, May). Velocity Skinning for Real‐time Stylized Skeletal Animation. In Computer Graphics Forum (Vol. 40, No. 2, pp. 549-561).[16] Kowalski, M. A., Markosian, L., Northrup, J. D., Bourdev, L., Barzel, R., Holden, L. S., & Hughes, J. F. (1999, July). Art-based rendering of fur, grass, and trees. In Proceedings of the 26th annual conference on Computer graphics and interactive techniques (pp. 433-438).[17] Strothotte, T., & Schlechtweg, S. (2002). Non-photorealistic computer graphics: modeling, rendering, and animation. Morgan Kaufmann.[18] DeCarlo, D., Finkelstein, A., Rusinkiewicz, S., & Santella, A. (2003). Suggestive contours for conveying shape. In ACM SIGGRAPH 2003 Papers (pp. 848-855).[19] Kalnins, R. D., Markosian, L., Meier, B. J., Kowalski, M. A., Lee, J. C., Davidson, P. L., ... & Finkelstein, A. (2002, July). WYSIWYG NPR: Drawing strokes directly on 3D models. In Proceedings of the 29th annual conference on Computer graphics and interactive techniques (pp. 755-762).[20] Imhof, N., Milliez, A., Jenal, F., Bauer, R., Gross, M., & Sumner, R. W. (2015, November). Fin textures for real-time painterly aesthetics. In Proceedings of the 8th ACM SIGGRAPH Conference on Motion in Games (pp. 227-235).[21] Bauer, A., & Salvati, M. (2022). The use of CG in Japanese animation. In ACM SIGGRAPH 2022 Courses (pp. 1-207).[22] Akenine-Mo, T., Haines, E., & Hoffman, N. (2018). Real-time rendering.[23] Kavan, L. (2014). Part I: direct skinning methods and deformation primitives. In ACM SIGG[RAPH (Vol. 2014, pp. 1-11).[24] Freestyle. Blender. https://docs.blender.org/manual/en/latest/render/freestyle/introduction.html 描述 碩士
國立政治大學
資訊科學系
109753143資料來源 http://thesis.lib.nccu.edu.tw/record/#G0109753143 資料類型 thesis dc.contributor.advisor 紀明德 zh_TW dc.contributor.advisor Chi, Ming-Te en_US dc.contributor.author (Authors) 林書廷 zh_TW dc.contributor.author (Authors) Lin, Shu-Ting en_US dc.creator (作者) 林書廷 zh_TW dc.creator (作者) Lin, Shu-Ting en_US dc.date (日期) 2023 en_US dc.date.accessioned 9-Mar-2023 18:37:28 (UTC+8) - dc.date.available 9-Mar-2023 18:37:28 (UTC+8) - dc.date.issued (上傳時間) 9-Mar-2023 18:37:28 (UTC+8) - dc.identifier (Other Identifiers) G0109753143 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/143836 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 資訊科學系 zh_TW dc.description (描述) 109753143 zh_TW dc.description.abstract (摘要) 日本的動畫產業，尤其在亞洲地區，發展至今已成為一門廣為人知的產業，也不斷地產生出許多世界級的作品，在以往傳統製作方式中，總會需要畫師耗費大量工時進行作畫才能製作出一款動畫，而隨時著間推進，有越來越多的數位輔助軟體被整合進製作流程中，試圖加速製作進度以及為畫面添加更多特色。在近期，開始有動畫製作公司採用三維建模的方式來製作動畫，也開始有些動畫作品中的角色直接使用全三維建模的方式製作，但有別於傳統的二維作畫，全三維製作的角色在激烈打鬥或運動的場景中，除了在風格上與二維作畫有所差距，也無法很好地表現出二維作畫中的速度與力道感，導致一般觀眾在觀看上時不時的出現難以言喻的違和感。本研究認為現今三維建模出來的角色在激烈運動時所造成的違和感，其原因為缺少了二維畫師在作畫時常會使用到的塗抹特效技術，因此我們透過幾何形變、邊緣成像，以及骨骼動畫的技術，讓這種日式動畫中的二維作畫特效也可以透過三維的方式成像出來。 zh_TW dc.description.abstract (摘要) The anime industry in Japan, especially in Asia, has developed into a well-known industry and has continuously produced many world-class works. In traditional production methods, animators would spend a lot of time drawing to create an animation, but with the advancements, more and more digital assistance software is integrated into the production process to try and speed up the production and add more features to the scene.Recently, some animation production companies have started using 3D modeling to create animations, and some animation works have characters that are directly made using full 3D modeling. However, unlike traditional 2D animations, the full 3D characters in intense fight or action scenes not only differ in style from 2D animations, but also cannot effectively convey the speed and force feeling in 2D animations, leading to an indescribable sense of discomfort among the general audience when watching.This research considers that the sense of discomfort caused by the intense motion of 3D-modeled characters today is due to the lack of smearing effect techniques that 2D animators often use when drawing. Therefore, through geometric deformation, edge rendering, and skeleton animation techniques, we can also display the 2D animation effects in Japanese animation in a 3D way. en_US dc.description.tableofcontents 第一章 緒論 11.1研究動機與目的 11.2問題描述 2第二章 相關研究 42.1卡通成像 42.2神經網路影像補幀 52.3非真實成像 62.4塗抹與形變 8第三章 研究方法與步驟 143.1環境設置 143.2系統架構 153.3 Preprocess 163.3.1 Level Grouping 163.4 Vertex Displacement 173.4.1 Displacement 173.4.2 Noising 193.4.3 Bending 213.4.4 Smoothing 263.5 Control Panel 27第四章 實驗結果 30第五章 問卷調查 33第六章 限制與未來展望 36第七章 結論與貢獻 38參考文獻 39 zh_TW dc.format.extent 3073483 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0109753143 en_US dc.subject (關鍵詞) 幾何形變 zh_TW dc.subject (關鍵詞) 邊緣成像 zh_TW dc.subject (關鍵詞) 骨骼動畫 zh_TW dc.subject (關鍵詞) Geometric Deformation en_US dc.subject (關鍵詞) Edge Rendering en_US dc.subject (關鍵詞) Skeletal Animation en_US dc.title (題名) 基於日本二維動畫風格的三轉二動畫塗抹特效技術 zh_TW dc.title (題名) Three to Two Dimensional Smear Effect Technique Based on Two Dimensional Japanese Animation Style en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) [1] Vielman, P., & Akleman, E. (2021). Animated Futurist Sculpting as Dynamic Implicit Shapes. In ACM SIGGRAPH 2021 Posters (pp. 1-2).[2] Cabral, B., & Leedom, L. C. (1993, September). Imaging vector fields using line integral convolution. In Proceedings of the 20th annual conference on Computer graphics and interactive techniques (pp. 263-270).[3] Motomura, J. C. (2015). GuiltyGearXrd’s Art Style: The X Factor Between 2D and 3D. Lecture at GDC.[4] Haller, M., Hanl, C., & Diephuis, J. (2004). Non-photorealistic rendering techniques for motion in computer games. Computers in Entertainment (CIE), 2(4), 11-11.[5] Barla, P., Thollot, J., & Markosian, L. (2006, June). X-toon: An extended toon shader. In Proceedings of the 4th international symposium on Non-photorealistic animation and rendering (pp. 127-132).[6] Petikam, L., Anjyo, K., & Rhee, T. (2021). Shading rig: Dynamic art-directable stylised shading for 3D characters. ACM Transactions on Graphics (TOG), 40(5), 1-14.[7] Schroeder, D., Coffey, D., & Keefe, D. (2010, June). Drawing with the flow: A sketch-based interface for illustrative visualization of 2D vector fields. In Proceedings of the Seventh Sketch-Based Interfaces and Modeling Symposium (pp. 49-56).[8] Bao, W., Lai, W. S., Ma, C., Zhang, X., Gao, Z., & Yang, M. H. (2019). Depth-aware video frame interpolation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 3703-3712).[9] Wang, X., & Yu, J. (2020). Learning to cartoonize using white-box cartoon representations. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 8090-8099).[10] Zheng, Q., Li, Z., & Bargteil, A. (2020). Learning to shadow hand-drawn sketches. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 7436-7445).[11] Perlin, K. (2002, July). Improving noise. In Proceedings of the 29th annual conference on Computer graphics and interactive techniques (pp. 681-682).[12] Igarashi, T., & Igarashi, Y. (2009). Implementing as-rigid-as-possible shape manipulation and surface flattening. journal of graphics, gpu, and game tools, 14(1), 17-30.[13] Hsu, S. C., Lee, I. H., & Wiseman, N. E. (1993, December). Skeletal strokes. In Proceedings of the 6th annual ACM symposium on User interface software and technology (pp. 197-206).[14] Zhang, J. E., Bang, S., Levin, D. I., & Jacobson, A. (2020). Complementary dynamics. arXiv preprint arXiv:2009.02462.[15] Rohmer, D., Tarini, M., Kalyanasundaram, N., Moshfeghifar, F., Cani, M. P., & Zordan, V. (2021, May). Velocity Skinning for Real‐time Stylized Skeletal Animation. In Computer Graphics Forum (Vol. 40, No. 2, pp. 549-561).[16] Kowalski, M. A., Markosian, L., Northrup, J. D., Bourdev, L., Barzel, R., Holden, L. S., & Hughes, J. F. (1999, July). Art-based rendering of fur, grass, and trees. In Proceedings of the 26th annual conference on Computer graphics and interactive techniques (pp. 433-438).[17] Strothotte, T., & Schlechtweg, S. (2002). Non-photorealistic computer graphics: modeling, rendering, and animation. Morgan Kaufmann.[18] DeCarlo, D., Finkelstein, A., Rusinkiewicz, S., & Santella, A. (2003). Suggestive contours for conveying shape. In ACM SIGGRAPH 2003 Papers (pp. 848-855).[19] Kalnins, R. D., Markosian, L., Meier, B. J., Kowalski, M. A., Lee, J. C., Davidson, P. L., ... & Finkelstein, A. (2002, July). WYSIWYG NPR: Drawing strokes directly on 3D models. In Proceedings of the 29th annual conference on Computer graphics and interactive techniques (pp. 755-762).[20] Imhof, N., Milliez, A., Jenal, F., Bauer, R., Gross, M., & Sumner, R. W. (2015, November). Fin textures for real-time painterly aesthetics. In Proceedings of the 8th ACM SIGGRAPH Conference on Motion in Games (pp. 227-235).[21] Bauer, A., & Salvati, M. (2022). The use of CG in Japanese animation. In ACM SIGGRAPH 2022 Courses (pp. 1-207).[22] Akenine-Mo, T., Haines, E., & Hoffman, N. (2018). Real-time rendering.[23] Kavan, L. (2014). Part I: direct skinning methods and deformation primitives. In ACM SIGG[RAPH (Vol. 2014, pp. 1-11).[24] Freestyle. Blender. https://docs.blender.org/manual/en/latest/render/freestyle/introduction.html zh_TW
