跳到主要內容

臺灣博碩士論文加值系統

(54.224.133.198) 您好!臺灣時間:2022/01/29 21:36
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

: 
twitterline
研究生:張任烜
論文名稱:有效的材質合成與影像轉移技術之研究
論文名稱(外文):A Study of Efficient Techniques for Texture Synthesis and Image Transfer
指導教授:王宗銘王宗銘引用關係
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:2002
畢業學年度:90
語文別:英文
論文頁數:101
中文關鍵詞:材質合成影像轉移貼圖材質材質影像處理
外文關鍵詞:Texture SynthesisImage TransferTexture MappingTextureImage Processing
相關次數:
  • 被引用被引用:6
  • 點閱點閱:2862
  • 評分評分:
  • 下載下載:493
  • 收藏至我的研究室書目清單書目收藏:1
  在電腦圖學(Computer Graphics)的領域裡,材質合成(Texture Synthesis)的研究是一個重要且值得探討的課題,故研究學者便發展出材質合成演算法以解決各式各樣的材質問題。在2001年學者Efros更提出了以材質區塊為基本合成單位(Patch-Based)之新的材質合成演算法,並將此演算法改良套用至影像轉移(Image Transfer)。此法雖能產生良好的合成效果,但仍在計算效能、影像品質等方面有所缺失,亟待改進。
  本篇論文針對Efros所提出的材質合成與影像轉移演算法之缺失,提出具體改進之道。我們採用以材質區塊為材質合成的基本單位,並提出新技術來加以改進先前學者之缺失。首先對於材質合成時,使用新的搜尋演算法來提升搜尋相似材質區塊之執行效能;其次,採用有效的最短誤差路徑(Minimum Error Path )方式來計算兩材質區塊間差異最小之路徑分佈位置;最後使用加權式線性羽化(Weighted Linear Feathering)的方式將材質區塊間明顯突出之部份混合淡化,因而致使影像品質大幅提升。此外,我們新提出一個「非疊代性影像轉移演算法」(Non-iterative Image Transfer Algorithm)。首先將目標影像依材質區塊之實質區域大小,採用由下而上、由左而右之順序依次取出目標影像之各個區域的特徵向量(Feature Vector)。接著在輸入影像中搜尋一些與這些特徵向量條件相吻合之材質區塊,然後逐一比對材質區塊之重疊區域(Overlap Region),找出最適當之材質區塊再將之貼附至輸出影像。我們以材質區塊與目標影像之相似程度為優先考量,其次再考慮材質區塊間的重疊黏接問題,如此影像轉移出之輸出影像將與目標影像大致相仿。
  經實驗結果顯示,我們的材質合成演算法在執行時效與影像品質上明顯優於Efros的方法,時效上之優勢係來自於使用有效的搜尋技巧。在影像品質方面,因我們採用最小誤差路徑與加權式線性羽化方式,因而大幅提升整體之視覺效果,其實驗結果也相當顯著。在影像轉移方面,我們提出「非疊代性影像轉移演算法」。僅需一次處理,就可完成影像轉移,而Efros卻必須重複數次的疊代方能完成。實驗上更證明我們的演算法比Efros方法更加優越,就僅單次影像轉移過程而言,我們的執行時便較Efros方式快了42.91 %的時間。在影像轉移後的影像品質上,我們的方法更是明顯的優於Efros的方法。不僅能使影像轉移後之結果與目標影像相仿,材質區塊間的銜接性亦是更加良好。此外,對於材質合成與影像轉移演算法,我們也提出更為廣泛的應用方向;例如:材質修補(Hole Filling)、材質延展(Texture Extrapolation)、物件摘除(Object Removal)、色彩轉移(Color Transfer)等均能展現具體之成效。
  總結本研究,我們認為我們所提出之有效的材質合成與影像轉移演算法,在執行時間、影像品質、廣泛的應用上均優於Efros學者之方法。由於以區塊為基礎之材質合成演算法是一種未來產生新材質的趨勢,且影像轉移演算法更是一種全新的研究方向,我們認為所提出之演算法已對此二議題做出了具體之貢獻。
Texture synthesis has been the subject of intensive research for many years in computer graphics community. Recently, Efros addressed this topic by presenting an algorithm referred to as image quilting, where a new image is synthesized by stitching together small patches of existing images. Efros also extended the algorithm to perform texture transfer, rendering an object with a texture taken from a different object. Efros’s approach produces good results for a wide range of textures. However, it demonstrates a severe drawback in the execution time, requiring several minutes for quilting and many iteration processes for image transfer. Another disadvantage of his method is that the synthesized results are normally with sharp edge in overlapped patch boundaries. In this thesis, we present a number of techniques to improve such drawbacks. We also provide several applications of texture synthesis and image transfer that have not been addressed by Efros. In particular, we utilize a new search algorithm to determine the best match texture patch to improve the computing performance. We present a technique, the minimum error path, to calculate the path position with the minimum but constraint variation in the overlapped patch boundaries. Apart from applying this technique, we blend the overlapped region with the weighted linear feathering method we proposed to reduce the visual perception of sharpness. For the image transfer, we present a novel algorithm, non-iterative image transfer algorithm. This algorithm utilizes the feature vectors constructed in the overlapped patch according to the order from the left and bottom region as well as from the right and top one. Given the feature vectors, our algorithm then efficiently determines a patch that is best match using the K-d tree search algorithm. We implemented our method as well as Efros’ approach, and collect some experimental results for comparison and analysis. We discover that our method works remarkably well, producing results that are better than Efros’ approach. In addition, our method significantly reduces a fraction of the computational cost, which requires not many but only a single iteration process for image transfer. Furthermore, our method is nearly 42.91% faster than our counterpart under the comparison on an iteration process. Finally, we present several applications of texture synthesis and image transfer, including hole filling, texture extrapolation, and color transfer. We conclude that this research has proposed efficient approach for texture synthesis and image transfer, and it has extended their feasibility by presenting several applications with very promising results.
第一章 緒論
  1.1簡介……………………………………………………………………1
  1.2論文架構………………………………………………………………4
第二章 相關研究
  2.1影像與材質影像之異同……………………………………………7
  2.2有限制性的材質合成演算法………………………………………9
    2.2.1具物理特性的模擬…………………………………………9
    2.2.2馬可夫隨機場的材質模型…………………………………10
  2.3無限制範圍之材質合成──以像素點為基礎之合成演算法……11
    2.3.1單一解析度材質合成方式…………………………………11
    2.3.2多層解析度材質合成方式…………………………………14
    2.3.3像素點為主之材質合成方式的缺失………………………16
  2.4無限制範圍之材質合成──以區塊為基礎的材質合成演算法…18
    2.4.1以區塊為主之材質合成演算法……………………………18
    2.4.2即時性區塊為基礎之材質合成演算法……………………23
  2.5影像轉移……………………………………………………………27
    2.5.1以像素點為基礎之影像轉移………………………………27
    2.5.2材質區塊為基礎的影像轉移………………………………29
  2.6研究分析與心得……………………………………………………31
第三章 有效的材質合成與影像轉移演算法
  3.1材質合成……………………………………………………………34
    3.1.1材質合成演算法……………………………………………34
    3.1.2選擇最相似之材質區塊……………………………………37
    3.1.3最小誤差路徑………………………………………………39
    3.1.4重疊材質區域之處理………………………………………41
    3.1.5改進後之材質合成的缺失…………………………………44
  3.2有效之材質合成……………………………………………………44
    3.2.1有效的材質合成演算法……………………………………45
    3.2.2輸入與輸出材質之遮罩……………………………………48
    3.2.3重疊材質區域處理…………………………………………50
  3.3影像轉移……………………………………………………………53
    3.3.1影像轉移演算法……………………………………………53
3.3.2材質與目標影像………………………………………………………55
    3.3.3特徵向量……………………………………………………56
第四章 實驗結果與分析
  4.1測試環境與測試模型………………………………………………57
  4.2以像素點與以材質區塊為基礎的材質合成演算法之比較………59
  4.3暴力搜尋法與Kd-tree搜尋方式對材質合成之影響與比較…… 64
  4.4加權式線性羽化處理對材質合成之影響與比較…………………65
  4.5材質區塊大小對材質合成之影響與比較…………………………68
  4.6重疊區域大小對材質合成之影響與比較…………………………70
  4.7疊代性與非疊代性影像轉移之比較………………………………71
  4.8相似區塊個數對影像轉移之影響與比較…………………………73
  4.9材質合成之應用……………………………………………………75
    4.9.1材質延展……………………………………………………75
    4.9.2具可編織性的材質合成……………………………………76
    4.9.3材質修補……………………………………………………77
    4.9.4物件摘除……………………………………………………79
  4.10影像轉移之應用………………………………………………… 80
    4.10.1影像轉移………………………………………………… 80
    4.10.2 材質轉移…………………………………………………81
    4.10.3色彩轉移………………………………………………… 82
第五章 結論與未來工作
  5.1結論…………………………………………………………………83
  5.2未來工作……………………………………………………………85
參考文獻…………………………………………………………………… 89
中英對照表………………………………………………………………… 95
英中對照表………………………………………………………………… 98
S. Arya, D. M. Mount, N. S. Netanyhu, R. Silverman, and A. Y. Wu, “An Optimal Algorithm for Approximate Nearest Neighbor Searching,” Journal of ACM, Vol. 45, No. 6, pp. 891-923, 1998.
M. Ashikhmin, “Synthesizing Natural Texture,” In ACM Symposium on Interactive 3D Graphics, pp. 217-226, March 2001.
J. F. Blinn and M. E. Newell, “Texture and Reflection in Computer Generated Images,” Communications of ACM, Vol. 19, No. 10, pp. 542-547, October 1976.
J. S. D. Bonet, “Multiresolution Sampling Procedure for Analysis and Synthesis of Texture Images,” In Proceedings of SIGGRAPH 1997, pp. 361-368, August 1997.
E. Catmull, “A Subdivision Algorithm for Computer Display of Curved Surfaces,” Ph.D. Thesis, Computer Science Department, University of Utah, Utah, USA, 1974.
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.
J. Davis, “Mosaics of Scenes with Moving Object,” In Proceedings of IEEE Computer Vision and Pattern Recognition (CVPR 1998), pp. 354-360, 1998.
J. M. Dischler, K. Maritaud, B. Levy, and D. Ghazanfarpour, “Texture Particles,” To appear in Computer Graphics Forum, (Eurogrpahics 2002), Vol. 21, No. 3, September 2002.
D. Kim and J. K. Hahn, “Projective Texture Mapping with Full Panorama,” To appear in Computer Graphics Forum, (Eurographics 2002), Vol. 21, No. 3, September 2002.
G. Doretto, S. Soatto, “Editable Dynamic Textures,” ACM SIGGRAPH 2002 Sketches and Applications, July 2002.
J. Dorsey, A. Edelman, J. Legakis, H. W. Jensen, and H. K. Pedersen, “Modeling and Rendering of Weathered Stone,” In Proceedings of SIGGRAPH 1999, pp. 225-234, August 1999.
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.
A. A. Efros and W. T. Freeman, “Image Quilting for Texture Synthesis and Transfer,” In Proceedings of SIGGRAPH 2001, pp. 341-346, August 2001.
D. D. Garber, “Computational Models for Texture Analysis and Texture Synthesis,” Ph.D. Thesis, Image Processing Institute University of Southern California, USA, 1981.
M. Haindl, 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.
P. Harrison, “A Non-Hierarchical Procedure for Re-synthesis of Complex Textures,” In Proceedings of Winter School of Computer Graphics 2001 (WSCG 2001), pp. 190-197, 2001.
D. J. Heeger and J. R. Bergen, “Pyramid-Based Texture Analysis /Synthesis,” In Proceedings of SIGGRAPH 1995, pp. 229-238, 1995.
A. Hertzmann, C. E. Jacobs, N. Oliver, B. Curless, and D. H. Salesin, “Image Analogies,” In Proceedings of SIGGRAPH 2001, pp. 327-340, August 2001.
I. T. Jollife, Principal Components Analysis, Springer-Verlag, New York, 1986.
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.
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.
J. P. Lewis, “Texture Synthesis for Digital Painting,” In Proceedings of SIGGRAPH 1984, pp. 245-252, 1984.
D. M. Mount, “ANN Programming Manual,” Technical Report, Department of Computer Science, University of Maryland, College Park, Maryland, USA, 1998.
R. Paget and I. D. Longstaff, “Texture Synthesis via a Non-causal Non-Parametric Multiscale Markov Random Field,” IEEE Transactions on Image Processing, Vol. 7, No. 6, pp. 925-931, June 1998.
K. Perlin, “An Image Synthesizer,” In Proceedings of SIGGRAPH 1985, pp. 287-296, July 1985.
J. Portilla and E. P. Simoncelli, “Texture Modeling and Synthesis Using Joint Statistics of Complex Wavelet Coefficients,” In Proceedings of the IEEE Workshop on Statistical and Computational Theories of Vision, pp. 73-80, 1999.
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.
K. Popat and R.W. Picard, “Novel Cluster-Based Probability Model for Texture Synthesis, Classification, and Compression,” In Proceeding of SPIE Visual Communications and Image Processing, pp. 756-768, 1993.
E. Praun, A. Finkelstein, and H. Hoppe, “Lapped Texture,” In Proceedings of SIGGRAPH 2000, pp. 456-470, July 2000.
E. Reinhard, M. Ashikhmin, B. Gooch, P. Shirley, “Color Transfer Between Images,” IEEE Computer Graphics and Applications, Vol. 21, No. 5, pp. 34-41, September/October 2001.
P. V. Sander, J. Snyder, S. J. Gortler, H. Hoppe, “Texture Mapping Progressive Meshes,” In Proceedings of SIGGRAPH 2001, pp. 409-416, 2001.
P. V. Sander, S. J. Gortler, J. Snyder, H. Hoppe, “Signal-Specialized Parameterization,” In Proceedings of Eurographics Workshop on Rendering (EWR 2002), 2002.
S. Soatto, G. Doretto, Y. N. Wu, "Dynamic Textures," In Proceedings of IEEE International Conference on Computer Vision 2001 (ICCV 2001), Vol. 2, pp. 439-446, July 2001.
C. Soler, M. P. Cani, and A. Angelidis, “Hierarchical Pattern Mapping,” To appear in Proceedings of SIGGRAPH 2002, July 2002.
R. Szeliski, and H. Y. Shum, “Creating Full View Panoramic Mosaics and Environment Maps,” In Proceedings of SIGGRAPH 1997, pp. 251-258, August 1997.
G. Turk, “Texture Synthesis on Surfaces,” In Proceedings of SIGGRAPH 2001, pp. 347-354, 2001.
Y. Wang and S. C. Zhu, “A Generative Method for Textured Motion: Analysis and Synthesis,” In Proceedings of European Conference on Computer Vision 2002 (ECCV 2002), pp. 583-598, 2002.
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.
L. Y. Wei and M. Levoy, “Fast Texture Synthesis Using Tree-Structured Vector Quantization,” In Proceedings of SIGGRAPH 2000, pp. 479-488, July 2000.
L. Y. Wei, “Texture Synthesis by Fixed Neighborhood Searching,” Ph.D. Thesis, Department of Computer Science, Stanford University, USA, November 2001.
L. Y. Wei, M. Levoy, “Order-Independent Texture Synthesis,” Technical Report TR-2002-01, Department of Computer Science, Stanford University, 2002.
A. Witkin and M. Kass, “Reaction-Diffusion Textures,” In Proceedings of SIGGRAPH 1991, pp. 299-308, July 1991.
S. P. Worley, ” A Cellular Texture Basis Function,” In Proceedings of SIGGRAPH 1996, pp. 291-294, August 1996.
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.
S. Zelinka and M. Garland, “Towards Real-Time Texture Synthesis with the Jump Map,” In Proceedings of Eurographics Workshop on Rendering (EWR 2002), 2002.
S. Zhu, Y. Wu, and D. Mumford, “Filters, Random Fields and Maximum Entropy (FRFME) — Toward a Unified Theory for Texture Modeling,” International Journal of Computer Vision, Vol. 27, No. 2, pp. 107-126, 1998.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊