跳到主要內容

臺灣博碩士論文加值系統

(34.204.169.230) 您好!臺灣時間:2024/02/26 05:33
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:龔彥勳
研究生(外文):Kung Yen Hsun
論文名稱:有效的邊界取樣材質合成之研究
論文名稱(外文):A Study of Effective Texture Synthesis by Edge Sampling
指導教授:王宗銘王宗銘引用關係
指導教授(外文):Chung-Ming Wang
學位類別:碩士
校院名稱:國立中興大學
系所名稱:資訊科學研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2003
畢業學年度:92
語文別:中文
論文頁數:126
中文關鍵詞:內容區塊內容像素材質內容合成圖材質內容圖結構性材質
外文關鍵詞:Content BlockContent PixelContent Synthesized ImageContent ImageStructural Texture
相關次數:
  • 被引用被引用:0
  • 點閱點閱:134
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
摘 要
材質合成(Texture Synthesis)在貼圖技術被普遍的運用且需要使用到解析度的材質下,成為了一個重要的研究議題。然而,目前的區塊材質合成演算法仍有下列四個缺點亟待解決。1.結構性材質合成時經常發生邊界破碎的情形。2.合成之材質缺乏多樣性,雖類似於來源材質但仍顯單調缺乏變化。3.需再加快材質合成的時間。4. 需有效的確保材質合成的邊界一致。
本篇論文針對目前區塊材質合成演算法之缺失,提出具體改進之道。針對邊界破碎的缺失,我們將傳統的單一步驟材質合成分為兩個獨立步驟,分別為材質邊界合成與材質內容合成。藉由利用邊界資訊,我們可以合成僅具有邊界資訊的邊界。接著,我們對僅具有邊界的輸出材質做內容材質的合成,產生了具有材質內容的合成材質。最後,我們對此合成材質進行修補,消除合成材質的邊界破碎情形。針對第二個缺失,我們在材質內容的合成過程中,使用多種材質內容來加以混合使用,使的所合成的輸出材質產生變化。此材質混合方式促使合成材質的變化,使之具有多種來源材質的特色,導致合成的材質的多樣化。針對第三種缺失,由於我們僅使用來源材質內的邊界資訊,故可簡化來源材質的資料量,相對的也大幅減少了合成時所需建立的龐大資料量。此也縮短比對所需的時間,加速了合成的時效性。針對第四種缺失,我們導入的兩階段的材質合成,避免了傳統材質合成時,在進行比對搜尋的過程中由於色彩的影響,導致選取不適合的區塊,影響到最後的合成品質。結構性材質不致因為此影響產生邊緣不一致的情形,增加了視覺的一致性,避免了視覺的突兀情形。兩階段的材質合成減低了重複合成的次數,提升了材質合成的有效性。
經實驗結果顯示,使用我們的演算法所進行的結構性材質合成的輸出材質影像中,已經看不到有邊界破碎的情形。此外,利用我們所提出的材質混合方式,來對材質進行合成促使我們的輸出材質除了具有相似於原始來源材質的特色外,同時也混合擁有其他材質的特色。此使得合成的材質更富多樣性。在合成的時效方面,我們的測試結果顯示,利用我們的演算法比傳統的區塊合成演算法減少了22.1%~66.1%之時間,平均減少46.3%的時間。此結果相當接近我們根據資料減少量在理論分析上認為約能減少2/3的合成時間。
綜合本研究,我們所提出之有效的邊界取樣材質合成演算法有效的改善了區塊材質合成中的四項缺失,也獲得了良好的合成結果與效能。此外,我們提出一種新的材質混合方式使得材質合成有了更為廣泛的實際應用範圍。我們認為本研究對材質合成的議題做出具體之貢獻。
Abstract
Texture mapping has been a popular technique used to increase the visual appearance of a scene. Texture synthesis algorithms intended to synthesize large texture images given a small source texture has under an intensive research. This thesis presents algorithms and techniques to overcome four drawbacks shown in synthesizing structural textures using conventional patch-based texture synthesis algorithm.
We partition the synthesis step into the “edge synthesis” step and “content synthesis” step to substitute the conventional process which is single-step, possibly producing faulty results. In the “edge synthesis” step, we extract the edge information in the source texture using common edge detection algorithms. We then synthesize an “edge texture” image containing edge information only. In the “content synthesis” step, however, we use the contents in the source texture and synthesize a new texture containing contents but with no edges. Results obtained from these two steps are then combined. Finally, we apply a restored process to remove the interrupted object boundaries. As a result, the final synthesis results contain synthesized textures with appealing appearance.
We also propose a new texture mixing algorithm. During the synthesis process, contents of various textures can be selected as users’ wish. When associating the “content synthesis” and “edge synthesis” step, textures with versatile looks can be generated. In addition, we can provide a control map including different diagrams to guide the combination. As a result, features of the mixing textures will has a similar appearance to the control map, producing interesting and visual attractive results.
Experimental results demonstrate that no interrupted object boundaries appear in the final synthesized textures. In addition, using the proposed texture mixing algorithm we are able to synthesize versatile textures. Furthermore, we can derive an output texture, performing as many characteristics as possible similar to the entire source textures. The synthesized time has been significantly reduced. Experimental results show that the time reduction is between 22.1% and 66.1% with 46.3% on average, in comparison to that of using conventional texture synthesis process. This statistics is very coincident to the theoretical analysis we performed which demonstrates that at most 2/3 of the synthesis time can be reduced.
In conclusion, our researches provide algorithms and techniques to solve four potential problems encountered in structural texture synthesis. Our algorithm, techniques are efficient, effective and feasible to provide synthesized textures with appealing visual effects.
目錄
第一章 簡介
1.1研究動機………………………………………………………………1
 1.2論文架構………………………………………………………………7
第二章 相關文獻回顧
 2.1材質及影像的不同……………………………………………………8
 2.2結構性材質……………………………………………………………9
 2.3像素材質合……………………………………………………………11
 2.4區塊材質合成…………………………………………………………13
  2.4.1 Efros之區塊材質合成演算法…………………………………13
  2.4.2 Liang的即時性之區塊材質合成演算法………………………17
 2.5區塊材質合成的做法及流程…………………………………………23
 2.6材質混合………………………………………………………………30
2.7研究分析與心得………………………………………………………36
第三章 有效的邊界取樣合成演算法
 3.1邊界取樣合成…………………………………………………………38
  3.1.1取得邊界資訊……………………………………………………39
  3.1.2邊界合成…………………………………………………………48
 3.2邊界破碎的處理………………………………………………………50
  3.2.1內容區塊之偵測及消除…………………………………………51
  3.2.2內容區塊的修補…………………………………………………54
  3.2.3材質內容重新合成………………………………………………55
 3.3材質混合及材質區塊的顏色轉移……………………………………59
  3.3.1材質混合…………………………………………………………59
  3.3.2內容區塊的色彩轉移……………………………………………62
  3.3.3色彩轉移…………………………………………………………63
第四章 測試結果與分析
 4.1測試環境與測試模型…………………………………………………68
 4.2結構性材質的合成結果………………………………………………70
 4.3結構性材質合成破碎的改善…………………………………………91
 4.4材質混合結果………………………………………………………100
  4.4.1隨機方式的材質混合…………………………………………101
  4.4.2加入控制圖之材質混合………………………………………105
  4.4.3色彩轉移合成…………………………………………………108
  4.5程式操作介面簡介………………………………………………110
第五章 結論與未來工作
  5.1結論………………………………………………………………113
  5.2未來工作…………………………………………………………115
參考文獻…………………………………………………………………118
中英對照表………………………………………………………………122
英中對照表………………………………………………………………124
特殊名詞解釋……………………………………………………………126
參考文獻
[ASHI2001] M. Ashikhmin, “Synthesizing Natural Texture,” In Proceedings of ACM Symposium on Interactive 3D Graphics, pp. 217-226, March 2001.
[ANDR1999] G. Andrew and K. B. Eom, “Color Texture Synthesis with 2-D Moving Average Model,” In Proceedings of 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing, Paper 2069, May 15-19, Phoenix, Arizona, 1999.
[BONE1997] J. S. D. Bonet, “Multiresolution Sampling Procedure for Analysis and Synthesis of Texture Images,” In Proceedings of SIGGRAPH 1997, pp. 361-368, August 1997.
[CROS1983] G. R. Cross and A. K. Jain, “Markov Random Field Texture Models,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. PAMI-5, No. 1, pp. 25-39, January 1983.
[DISC2002] J. M. Dischler, K. Maritaud, B. Levy, and D. Ghazanfarpour, “Texture Particles,” Computer Graphics Forum, (Eurogrpahics 2002), Vol. 21, No. 3, pp. 401-410, September 2002.
[EFRO1999] A. A. Efros and T. Leung, “Texture Synthesis by Non-Parametric Sampling,” In Proceeding of International Conference on Computer Vision, Vol. 2, pp. 1033-1038, September 1999.
[EFRO2001] A. A. Efros and W. T. Freeman, “Image Quilting for Texture Synthesis and Transfer,” In Proceedings of SIGGRAPH 2001, pp. 341-346, August 2001.
[HAIN2002] M. Haindl and V. Havlicek, “A Simple Multispectral Multiresolution Markov Texture Model,” In Proceedings of the 2nd International Workshop on Texture Analysis and Synthesis, pp. 63-66, 2002.
[HEEG1995] D. J. Heeger and J. R. Bergen, “Pyramid-Based Texture Analysis /Synthesis,” In Proceedings of SIGGRAPH 1995, pp. 229-238, 1995.
[JOLL1986] I. T. Jollife, Principal Components Analysis, Springer-Verlag, New York, 1986.
[JOSE2000] Z. B. Joseph, R. E. Yaniv, D. Lischinski, and M. Werman, “Texture Mixing and Texture Movie Synthesis Using Statistical Learning,” In Proceeding of SIGGRAPH 2000 Sketch, pp. 266-266, July 2000.
[JOSE2001] Z. B. Joseph, R. E. Yaniv, D. Lischinski, and M. Werman, “Texture Mixing and Texture Movie Synthesis Using Statistical Learning,” IEEE Transactions on Visualization and Computer Graphics, Vol. 7, No. 2, pp. 120-134, April-June 2001.
[KWAT2003] V. Kwatra, A. Schödl, I. Essa, G. Turk and A. Bobick, “Image and Video Synthesis Using Graph Cuts,” In Proceeding of ACM Transactions on Graphics, SIGGRAPH 2003, Vol. 22, pp.277-286, July 2003.
[LIAN2001] L. Liang, C. Liu, Y. Q. Xu, B. Guo, and H. Y. Shum, “Real-Time Texture Synthesis by Patch-Based Sampling,” ACM Transactions on Graphics, Vol. 20, No.3, pp. 127-150, July 2001.
[MOUN1998] D. M. Mount, ANN Programming Manual, Technical Report, Department of Computer Science, University of Maryland, College Park, Maryland, USA, 1998.
[NEAL2003] A. Nealen and M. Alexa, “Hybrid Texture Synthesis,” In Proceedings of Eurographics Symposium on Rendering 2003, pp. 97-105, 2003.
[PRAU2000] E. Praun, A. Finkelstein, and H. Hoppe, “Lapped Texture,” In Proceedings of SIGGRAPH 2000, pp. 456-470, July 2000.
[PORT2000] J. Portilla and E. P. Simoncelli, “A Parametric Texture Model Based on Joint Statistics of Complex Wavelet Coefficients,” International Journal of Computer Vision, Vol. 40, No. 1, pp. 49-70, October 2000.
[REIN2001] E. Reinhard, M. Ashikhmin, B. Gooch, and P. Shirley, “Color Transfer Between Images,” IEEE Computer Graphics and Applications, Vol. 21, No. 5, pp. 34-40, September/October 2001.
[TONI2002] L. Tonietto and M. Walter, “Towards Local Control for Image-Based Texture Synthesis,” In Proceedings of XV Brazilian Symposium on Computer Graphics and Image (SIBGRAPI’02), pp. 252-258, October 07-10, Fortaleza-CE, Brazil, 2002.
[WEI1999] L. Y. Wei, “Deterministic Texture Analysis and Synthesis Using Tree Structure Vector Quantization,” In Proceedings of XII Brazilian Symposium on Computer Graphics and Image (SIBGRAPI 1999), pp. 207-213, October 1999.
[WEI2000] L. Y. Wei and M. Levoy, “Fast Texture Synthesis Using Tree-Structured Vector Quantization,” In Proceedings of SIGGRAPH 2000, pp. 479-488, July 2000.
[WEI2001] L. Y. Wei, Texture Synthesis by Fixed Neighborhood Searching, Ph.D. Thesis, Department of Computer Science, Stanford University, USA, November 2001.
[WELS2002] T. Welsh, M. Ashikhmin, and K. Mueller, “Transferring Color to Grayscale Images,” In Proceedings of SIGGRAPH 2002, pp. 277-280, July 2002.
[XUYQ2000] Y. Q. Xu, B. Guo, and H. Y. Shum, “Chaos Mosaic: Fast and Memory Efficient Texture Synthesis,” Microsoft Research Technical Reports, MsR-TR-2000-32, April 2000.
[ZELI2002] S. Zelinka and M. Garland, “Towards Real-Time Texture Synthesis with the Jump Map,” In Proceedings of Eurographics Workshop on Rendering (EGWR 2002), pp. 20-27, 2002.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top