非擬真成像(Non-Photorealistic Rendering)為圖學眾多領域中的一環，主要用於模擬各種藝術繪畫風格。在不同藝術風格的模擬上，皆有相關的研究。然而，大部分的藝術風格皆為平面藝術，一般觀賞者無法從畫作中感受藝術家所要表達的立體感。因此本研究希望針對各種畫作產生相對應深度圖，並在立體螢幕呈現立體風格化藝術。

在許多研究中，對於真實影像深度圖的產生有各種不同的演算法，也都各有其優缺點。然而在所有自動生成深度圖的演算法中，都存在著破洞及鋸齒狀的缺點，造成立體影像在觀賞上的缺陷，因此在本篇研究中，我們提供一直覺介面，讓使用者分割影像，並指定相對應的深度。在深度的指定上，我們利用Harmonic內插來保證深度在各個區塊中的連續性，使其在視覺效果上不會產生突兀的感覺。除了靜態的筆觸擺放，我們更進一步利用筆觸的流動，讓原本靜態的畫作，呈現出更活潑生動的風格，加上立體效果的呈現，將會讓觀看者，有截然不同的全新感受。

Non-photorealistic Rendering (NPR) is one part of arbitrary research fields in Computer Graphics and primarily used to simulate every kind of artistic painting styles. There are existing researches from different simulations of artistic styles. However, almost artistic styles are plane arts. General observers cannot feel the stereoscopic representation which the artists would like to express from the paintings. Therefore, this study aims to produce the corresponding depth map for a variety of paintings and present the style of rendering three-dimensional art in the stereoscopic screen.

According to many studies, there are different algorithms including advantages and disadvantages respectively from the production for depth generation from true image. Nevertheless, in all automatically generated depth map algorithms, it exists holes and the zigzag fault causing defects in three-dimensional image observation. So, in this study, we provide an intuitive interface that allows users to split the image and specify the corresponding depth. From the point of depth, we apply harmonic interpolation to prove the depth in every continuity which make impressive feelings from the visual effects. In addition to static display strokes, we further use of animated strokes, so that the original static paintings appear a more vivid and lively style. Finally, the extra demonstration of the three-dimensional effect will bring the observers a brand-new experience.

[1]Connelly Barnes, Eli Shechtman, Adam Finkelstein, and Dan~B Goldman. PatchMatch : A Randomized Correspondence Algorithm for Structural Image Editing.
[2]W~a Barrett and E~N Mortensen.Interactive live-wire boundary extraction. Medical image analysis}, 1(4):331--41, September 1997.
[3]S~Battiato, S~Curti, M~La Cascia, M~Tortora, E~Scordato, Universit Catania, and Informatica Catania. Depth-Map Generation by Image Classification.5302:95--104, 2004.
[4]R-p~M Berretty, F~J Peters, and G~T~G Volleberg.Real Time Rendering for Multiview Autostereoscopic.6055:1--12, 2006.
[5]Adrien Bousseau, Fabrice Neyret, Thollot,and David Salesin.Video watercolorization using bidirectional texture advection.ACM SIGGRAPH 2007 papers on - SIGGRAPH '07}, page 104, 2007.
[6]Shenchang~Eric Chen and Lance Williams.View interpolation for image synthesis.Proceedings of the 20th annual conference on Computer graphics and interactive techniques - SIGGRAPH 93, pages 279--288, 1993.
[7]Cassidy~J Curtis, Sean~E Anderson, Joshua~E Seims, and David~H Salesin. Computer-Generated Watercolor.1859.
[8]Robust Analysis of Feature Spaces: Color Image Segmentation.Proc. of IEEE Conference on Computer Vision and Pattern Recognition, 5302:750--755, 1997.
[9]David Doria and Richard~J. Radke. Filling large holes in LiDAR data by inpainting depth gradients.2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, pages 65--72, June 2012.
[10]James Hays and Irfan Essa. Image and Video Based Painterly Animation.(1), 2000.
[11]Liu He, Michael Bleyer, and Margrit Gelautz. Object Removal by Depth-guided Inpainting.
[12]Aaron Hertzmann. Painterly rendering with curved brush strokes of multiple sizes. Proceedings of the 25th annual conference on Computer graphics and interactive techniques - SIGGRAPH '98, pages 453--460, 1998.
[13]Henry Kang, Seungyong Lee, and Charles~K Chui.Flow-based image abstraction.IEEE transactions on visualization and computer graphics,15(1):62--76, 2009.
[14]Henry Kang and St~Louis.Coherent Line Drawing.2002.
[15]Leith~Casey Leedom and Lawrence Livermore.Imaging Vector Fields Using Line Integral Convolution.
[16]Huang Chen Lee~Lo Liu, Wu.基於3D顯示器格式之即時3D內容合成技術.2010.
[17]Thomas Luft.Real-Time Watercolor Illustrations of Plants Using a Blurred Depth Test.1997.
[18]Rene Klein~Gunnewiek Ping~Li.On Creating Depth Maps from Monoscopic Video using Structure from Motion.Proc. of IEEE Workshop on Content Generation and Coding for 3D-television, 5302:508--515, 2006.
[19]Jian Sun and Jiaya Jia.Image Completion with Structure Propagation.2003.
[20]O~Wang, M~Lang, M~Frei, A~Hornung, A~Smolic, and M~Gross.StereoBrush : Interactive 2D to 3D Conversion Using Discontinuous Warps.2001.
[21]Georges Winkenbach, David~H Salesin, Georges Winkenbach, and David~H Salesin. Computer-Generated Pen-and-Ink Illustration Computer-Generated Pen-and-Ink Illustration.1994.
[22]Chih-Yuan Yao, Ming-Te Chi, Tong-Yee Lee, and Tao Ju.Region-based line field design using harmonic functions.IEEE transactions on visualization and computer graphics,18(6):902--13, June 2012.
[23]L.~Zhang and W.J. Tam.Stereoscopic Image Generation Based on Depth Images for 3D TV.IEEE Transactions on Broadcasting, 51(2):191--199, June 2005.