人或擬人生物佔眾多動畫主題的大部份，而要使人物動畫看起來栩栩如生，除了適當的臉部表情外，能夠傳達人物情感的肢體動作更是不可或缺。本研究的目標在於以電腦程序產生帶有情緒成份之人物肢體動畫。此目標包含兩個子目標：第一、設計以人類肢體動作為目標的參數化程序，以提高程序之重用性及泛用性，降低製作程序式動畫的成本，並製作出以關鍵格為基礎之人物動畫；第二、將我們製作的動畫加入風格，並以心理學實驗驗證人物的動作和情緒的關聯。我們的實驗先將風格套用於走路動作上，來證明我們操弄風格的方法符合大眾的認知。再者，我們針對走路動作嘗試以實驗找出風格和情緒的對映，再將此對映關係套用到具特定情緒意涵的動作上，以證明這些對映有助於情緒的表達。 / Human or human-like creatures are the main subjects of computer animations. In addition to facial expression, body gestures and motions are also indispensi-ble components for realistic character animation. The goal of this research is to create emotional character animation with computer procedures. This goal may contain two subgoals: first, we aim to design parameterizable animation proce-dures for human body motions in order to reduce the cost of producing key-frame based character animations with improved generality and reusability; second, we incorporate style into procedural animation and validate the relation model between emotion and motion with psychology experiments. We first ap-plied different styles into the walking motion and conducted experiments to see if the participants can agree with the way that we manipulate the style parame-ters. Furthermore, for the walking motion, we conduct experiments to find the mapping from the emotion parameters to the style parameters. Then we applied this mapping to emotion-specific motions to see if the animations perceived by the users can be further enhanced.

在我國近來大力推展的各項數位內容核心產業當中，電腦動畫產業具有相當龐大潛在產值及經濟效益，為主要發展重點。但我國動畫產業在過去長期代工的背景之下，面臨極大的瓶頸。本研究希望藉由深入觀察與剖析目前國內已獲得初步成果的動畫公司之智慧資本建立與累積過程，來萃取出適合於我國動畫事業發展的一條途徑，從智慧資本的觀點來探討我國動畫事業經營與建立競爭優勢之關鍵為何，提供產界與學界作為參考。 本研究採取個案研究方式，選擇一家目前國內已經獲得相當成果的動畫公司－甲馬創意股份有限公司，深入剖析其智慧資本建立與累積過程，希望能夠回答以下幾個問題： 1. 動畫事業的智慧資本內涵為何？ 2. 在個案公司發展的過程中，智慧資本各構面間的相對比重有何變化？形成變化的原因？各智慧資本構面內容的變化又是如何？ 3. 各項智慧資本構面對個案公司而言，有著如何不同的重要性？最為關鍵的是何種智慧資本？ 4. 個案公司所從事的各種智慧資本建構活動及其原有智慧資本如何影響智慧資本的建立與累積？ 本研究之結論可摘要如下： 一、 動畫事業的智慧資本可為分四個構面具體描述其內涵 1. 人力資本：大致可分為動畫製作與經營管理兩方面。亦包含組織成員的創新能力、思考靈活度、人格特質、工作熱忱、互動情況、學習能力、抗壓性等。 2. 關係資本：大致可分為業務開發、動畫製作、原創者整合、行銷資源與資金來源等五種。 3. 流程資本：主要包含動畫創製作、動畫專案管理、動畫創作成果管理及動畫產品行銷規劃等方面之工作流程、原則、制度、採用的工具及特殊方法等。 4. 創新資本：包含有助創新的公司文化、經營策略與人員訓練方式，提升創作潛力的創作模式或原則、管理方式、以及開發新動畫產品的潛力與效率等。亦包含創新成果本身，及管理、運用與保護創新、創作成果之能力。 二、 智慧資本構面的比重與內容會隨事業的發展而變化 5. 個案公司剛成立時，人力資本與關係資本佔智慧資本總量的最大比例。發展的歷程中，關係與流程資本成為比重最大的兩項智慧資本。 待發展漸趨成熟，四種不同智慧資本的比重趨於平均。 6. 由各智慧資本構面的比重變化可以看出在個案公司的發展過程中，組織能力由人力與關係等基本的資源，擴散到深植於組織的流程與組織價值，形成較為深厚的創新能力。 7. 隨著個案公司的發展，人力、關係與流程等智慧資本的內容，朝向企劃、管理與行銷方向發展。而創新資本的累積也將受到組織對創新與創意之管理能力的影響。亦即對個案公司而言，強大的企劃、管理、行銷與資源整合能力成為事業持續成長的關鍵。 三、 不同智慧資本構面之重要性有所不同 8. 人力資本在個案公司發展初期具有較大的影響力，但關係資本與流程資本才是支持整體事業不斷成長的重要關鍵。 9. 人力資本與關係資本對於個案公司而言，扮演著刺激各項智慧資本建立與累積的重要角色。 四、 不同智慧資本建構活動及組織原有智慧資本，會對智慧資本的建立與累積產生不同的影響 10. 人力資本的建立與累積主要靠著「實驗」與「輸入智慧資本」兩種智慧資本建構活動，又受組織原有人力資本與關係資本影響最大。 11. 關係資本主要靠著企業「解決問題」的過程來建構，而又受組織原有關係資本與創新資本之影響最大。 12. 維持與繼續深耕關係資本的關鍵，在於組織的創新與執行能力。 13. 流程資本的建立與累積主要靠著「解決問題」與「執行與整合」兩種智慧資本建構活動，又受組織原有人力資本與關係資本影響最大。 14. 建立與累積流程資本時，較難直接從組織外部輸入既定流程加以套用，必須在公司開發專案的過程中逐漸摸索出最適合本身組織運作方式與組織文化的創作及管理流程。 15. 創新資本主要靠著企業「解決問題」的過程來建構，而又受組織原有人力資本之影響最大。 16. 在個案公司發展初期，創新資本的建立與累積相較於其他智慧資本來說較為緩慢，但各項智慧資本累積充足後之相互加乘效果，使得創新資本加速成長。 17. 「解決問題」與「實驗」兩種智慧資本建構活動容易產生「創造」的建構效果；「解決問題」與「執行整合」則容易產生「改良」的建構效果；「解決問題」、「實驗」與「輸入智慧資本」三種建構活動，都容易產生「增長」的建構效果。 / Due to its great economic potential, computer animation is a main focus in the digital content industry. But for long, most of the animation companies or studios in Taiwan have been focusing on animation manufacturing which only brings little profit rather than on creating their own original content; this has greatly limited the development of the whole computer animation industry in Taiwan. Luckily, there are still some animation companies in Taiwan which have been trying hard to develop their own content. JAMAR IDEA PRODUTION Ltd. is one of these animation companies and has made some remarkable achievements. From the perspective of intellectual capital, this research digs deeply into JAMAR and wish to find some useful clues to help effectively and efficiently build up an animation company’s intellectual capital and competitive strengths. The objective of this research is to answer the following questions: 1. What are the components of an animation company’s intellectual capital? 2. How did the relative weight and the composition of each intellectual capital dimension change along with the development of JAMAR? 3. How different was each intellectual capital dimension regarding its importance to JAMAR? What were the most critical dimensions? 4. How did JAMAR’s company activities and intellectual capital affect the development of each intellectual capital dimension? The conclusions of this research can be summarized as below: A. The components of an animation company’s intellectual capital can be described according to the following four dimensions. 1. Human Capital: An animation company’s human capital can be divided into two categories, that is, animation production and management. Also, company members’ enthusiasm for work, personality, attitudes, ability to innovate, to think creatively, and to learn new things altogether form the company’s human capital. 2. Relational Capital: An animation company’s relational capital can be divided into five categories including business development, animation production, the cooperation with artists, marketing channels, and the sources of capital or investment. 3. Process Capital: An animation company’s process capital mainly includes the working processes, principles, institutions, tools and methods taken in the company regarding the following four categories: animation creation and production, animation project management, animation works management, and the marketing of animation products. 4. Innovation Capital: An animation company’s innovation capital includes the company culture, the strategies, and the training programs that help build an innovative atmosphere in the company. Also, innovation capital includes the approaches that can enhance company’s potential to innovate. And of course, an animation company’s innovative animation films, products, or honors obtained for its innovative works are part of its innovation capital. B. The relative weight and the composition of each intellectual capital dimension changed along with the development of JAMAR. 5. In the early stage, human capital and relational capital had the biggest relative weights among all four dimensions. In the mid stage, relational capital and process capital became the most important two dimensions. And in the last stage, when the company was more matured, the distribution of these four dimensions’ relative weights tended to be more balanced. 6. From this relative weight change we can see the company’s ability shifted from the more basic human capital and relational capital to the process capital, which better embedded within an organization, and finally stimulated a greater ability to innovate. 7. The compositions of human capital, relational capital, and process capital developed towards a direction more focused on project planning, management, and marketing. And the development of innovation capital was also affected by the company’s ability to manage innovations and creativities. C. The importance of each intellectual capital dimension was different. 8. Human capital had a greater importance in the early stage of the company, but relational capital and process capital were more critical to sustain the continuous growth of the company. 9. Human capital and relational capital acted as an important stimulant to the development of the company’s intellectual capital. D. The company’s activities and intellectual capitals differently affected the development of each intellectual capital dimension. 10. Human capital was mainly built up through “experimenting and prototyping” and “importing intellectual capital” and was mostly affected by the company’s human capital and relational capital. 11. Relational capital was mainly built up through “problem solving” and was mostly affected by the company’s relational capital and innovation capital. 12. The ability to innovate and execute is critical to sustain and reinforce relational capital. 13. Process capital was mainly built up through “problem solving” and “implementing and integrating”and was mostly affected by the company’s human capital and relational capital. 14. It was not easy to import process capital directly from other organizations. Process capital was usually built up gradually over the course of running animation projects. 15. Innovation capital was mainly built up through “problem solving” and was mostly affected by the company’s human capital. 16. Innovation capital grew relatively slow in the early stage of the company, but was then simulated to accelerate its development when all the other three capitals were accumulated to a certain amount. 17. “Problem solving” and “experimenting and prototyping” tended to generate an effect of “creation”. “Problem solving” and “implementing and integrating”tended to generate an effect of “improvement”. “Problem solving”, “experimenting and prototyping”, and “importing intellectual capital” tended to generate an effect of “increase”.

程序式動畫是一種根據使用者所提供的高階運動參數，自動產生動畫的方法。藉著高階的運動參數，程序式動畫比運動擷取資料有著更高的彈性。使用者可透過調整參數，輕易地讓動畫滿足情境上所需的限制。但如何調整適當的運動參數以產生擬真的動畫仍屬不易，因此程序式動畫常有在視覺上觀感不自然的問題。本研究的目標是，將運動擷取資料擬真的要素，帶到程序式動畫之中，以改進程序式動畫的品質。我們將問題定義成一個最佳化問題：給定一段運動擷取資料，系統該如何調整程序式動畫之參數，使得程序式動畫與運動擷取資料的差距盡可能地縮小？我們的系統可以參考一段運動擷取資料，以最佳化演算法，自動調整程序式動畫的參數，搜尋能產生出與運動擷取資料最為相似的運動參數。為了進一步讓產生之動畫符合環境的限制需求，多組最佳化過後的運動參數可以再透過內插，重新產生出一組符合限制需求的運動參數。實驗結果顯示，我們的方法不但使程序式動畫得以保留原來彈性的優點，也改善了程序式動畫常有的視覺觀感不自然的缺點。 / Procedural animation provides a way for a user to generate animation according to the high-level motion parameters that the user supplies. With the high-level motion parameters, procedural animation has the flexibility of generating animation accommodating the requested constraints in a scenario. However, tuning parameters to generate realistic animations usually is a difficult task. Therefore, animations produced with this approach often have the drawback of unrealistic-looking. Our goal is to improve the quality of procedural animation by bringing the naturalness of motion capture data into procedural animation. We model our problem as an optimization problem: given a motion captured clip, how does the system tune the motion parameters in an animation procedure to minimize the difference between animations produced by a procedure and captured in a motion clip? Our proposed system takes a motion captured clip as a reference and tunes the motion parameters of the animation procedure with an optimization algorithm. In order to generate animation satisfying environmental constraints, multiple optimized motion parameters can be interpolated to create a new set of motion parameters which can also satisfy the constraints. Our experimental results show that our method not only retains the flexibility of procedural animation, but also enhances the quality of procedural animation.

動作擷取法是現今相當受到歡迎的角色動作產生方法，而一般多是使用已擷取好的動作，以人工的方式將數個不同的動作混合以產生出所需的動作。但想要大量產生符合需求的混合動作仍相當不容易，因此有人提出了「動作圖」這個方法。動作圖是一種根據使用者所給定的動作擷取資料集合，經過自動化的計算找出各個動作資料之間可以連接的動作片段。藉由這個自動化的程序，各個動作擷取資料可以相互連接起來，達到在不同的動作間平順轉換，且同時保有原動作擷取資料擬真特性的目的。但縱使有上述的好處，目前動作圖的技術僅能就所擷取的全身動作進行串接，品質與彈性往往決定於一開始動作擷取資料的準備，因此如何讓既有的全身動作資料得以分解再利用，以發揮最大的價值，是一個重要的問題。在本研究中，我們提出了一個階層式的動作圖結構名為多層式動作圖，在這個多層式動作圖的結構中，我們將身體的動作區分成數個部位，分別計算各自的動作圖後再合併成一個多層式的架構，而合併的過程中我們提出「整體動作相似度」的計算方式，以做為兩個動作是否容易轉接的比較依據。我們也提出了在不同階層間動作圖運作的規則，以使計算的複雜度及系統的可用性取得合理的平衡。此外，我們更進一步提出名為Motion Script的簡易語意描述語言，來輔助控制這個具有高複雜度的動作圖結構。實驗的結果顯示，我們的方法可以即時根據使用者的指令，搜尋並產生出原動作資料所沒有的動作組合。與傳統的動作圖相比，我們的方法能更進一步的發揮原動作擷取資料的價值，以有系統的方式讓動作組合自動產生更具豐富性及彈性。 / Motion capture is a popular method for generating realistic character animation. In most applications, a motion usually is prepared by manually blending existing captured motion clips to generate a desired motion clip. However, finding a good transition points manually for two motion clips is a time-consuming task and cannot be scaled up easily. Motion Graph is a technique that has been proposed to automate this process by finding suitable connection points and the corresponding transition motions between motion data. With this automatic procedure, motions captured separately can be smoothly connected while keeping the realism of the captured motions. However, most motion graph techniques only consider the transition of full-body motions in two motion clips, and therefore, the resulting motion .depends on the variety of motions available in the motion database. It is an important issue to be able to compose new motion clips as much as possible with given motion capture database. In this research, we propose a hierarchical motion graph structure called Multi-Layered Motion Graph. In this structure, we divide motion data into layers of parts depending on the articulated structure of human body, and then compute a motion graph for each part of the motion. We then combine these motion graphs into an interconnected hierarchical structure. In order to facilitate the composition of motions for different parts from different motion clips, we propose a new metric called Overall Motion Similarity to find reasonable composition of motions in run time. We also propose several rules about how to traverse the motion graphs in different layers to generate feasible motions. Furthermore, we have designed a scripting language called Motion Script to facilitate the specification and search of desirable animation to be generated. Our experimental results reveal that our method is able to compose animations that the original motion graph cannot generate in real time. Compared to the traditional motion graph method, our method is able to make good use of existing motion capture library to compose new motions in a systematic way.

台灣3D電腦動畫廠商目前以承接國外大廠動畫製作訂單為主要業務。但隨著3D動畫軟硬體設備成本的降低，人力成本低廉之開發中國家3D動畫廠商開始崛起，威脅到台灣3D動畫廠商的代工地位。解決此困境的策略有二：一是朝向內容原創價值活動方向發展，另一則是加強本身的代工競爭能力。 受限於市場及經驗不足等因素，台灣廠商欲發展原創能力還有很長遠的路要走，因此本研究著重於如何加強代工競爭能力。台灣許多產業都發展出優秀的代工模式廠商，而3D動畫產業則尚處於幼稚期，廠商接單後多半獨力完成所有製作工作。因此本研究以在代工模式上表現優異之台積電及廣達電腦為比較對象，並以國內最大3D動畫廠商西基動畫為個案研究對象，分析探討適合3D動畫廠商之「代工廠商供應模式」。 本研究先歸納整理四個「垂直整合或委外生產決策」考慮因素構面，亦即成本構面、產品構面、技術構面以及供應商(產業)構面，利用此四個因素構面分析台積電、廣達之現有供應體系模式，然後比較西基與台積電、廣達在這四個構面上不同的條件及特色，最後分析出適合西基之代工廠商供應體系模式。 / Receiving outsourcing project orders from foreign major companies is the primary business of the 3D Animation firms in Taiwan currently. However, since the cost of the infrastructure for animation production has reduced, it is easier for developing countries to enter this industry, where labor cost is lower. Accordingly, Taiwan’s position in the value chain of the animation industry is threatened. Two solutions have been proposed in order to solve this problem. First, animation firms in Taiwan should extend to the high value-added content developing activities. Second, Taiwanese animation firms should improve their capability and retain their competence. This research focuses on how to improve the capability of animation firms in Taiwan, since it is still immature for them to transform into content developers, owing to the lack of experience and limitation of market size. Animation industry in Taiwan is in its infancy: most of the animation firms finish project orders independently. On the contrary, many industries in Taiwan, such as the computer industry, have developed excellent OEM/ODM models. Therefore, this research adopts case study method, taking CGCG Interactive as target, and compares it with the models of TSMC and Quanta Computer to figure out a suitable OEM supplier’s model in 3D animation industry. This research first concludes that there are four dimensions concerning the decision making process on selecting vertical integration or outsourcing strategies. These dimensions are cost, product, technology, and supplier (industry). Then these dimensions are used to analyze the supply model of TSMC and Quanta Computer so as to propose an appropriate supply model CGCG Interactive.

在目前3D虛擬環境中，虛擬人物的動作多半是以動作抓取等離線方式錄製後，再以罐裝動作的方式呈現。該動作經過編碼後會以固定的格式進行傳送，然後由客戶端撥放該動畫內容。通常而言，固定的格式規範會限制電腦動畫表現與延展的能力。這篇論文我們提出了一套以XML為基礎的動畫語言，稱為eXtensible Animation Markup Language(XAML)來解決這樣的問題。這套語言設計的目的是為了讓開發者能夠彈性地選擇不同層次的指定方式來產生虛擬演員的動畫；同時使用者可以藉由已經定義好的動畫合成新的動畫內容，或是更改已定義動畫的部分內容來產生一套新的動畫。除此之外，XAML為客製化腳本語言提供延展擴充的機制，開發者可以透過plug-in、內嵌XAML引擎或轉換腳本等方式達到擴充XAML的目的。我們同時使用JAVA實作了一套能夠解譯XAML的動畫引擎，使用者不但可以利用XAML腳本命令產生相對應的3D動畫顯示，也可以透過該動畫引擎所提供的函式庫對場景中的3D物件進行控制。另外，我們也設計了一個具語音對話功能的多人虛擬環境系統，以驗證XAML語言的可行性及有效性。 / Character animations on most virtual environment systems are canned motions created off-line through motion capture techniques. The motions are then en-coded and transmitted with a fixed format and played at the client side. The rigid specification format for computer animation and multimedia presentation in general has greatly affected the development of 3D contents. In this thesis, we propose an XML-based scripting language, called eXtensible Animation Markup Language (XAML). The language is designed to describe character animations at various command levels and to compose a new animation from existing ani-mation clips. Furthermore, one can use plug-in, embeding or translation to in-corporate other customized scripting languages or new functions into XAML. We have implemented an animation engine in Java that can interpret the script-ing language and render 3D animations based on the user’s interactive XAML commands or the provided application programming interface. In addition, we have designed a speech-enabled multi-user virtual environment system based on XAML to verify the feasibility and effectiveness of such a language.

近年來，智慧型互動電視的應用是不少數位生活空間研究的焦點之一。我們認為，好的互動式數位電視系統必須有生動靈活的使用介面與使用者互動。在本研究中，我們提出以智慧型3D動畫角色為介面之互動數位電視系統，希望可以藉由智慧型3D動畫角色在介面上的呈現，加強使用者於互動數位電視系統的使用經驗。在我們過去所開發的互動數位電視系統SITV上，有許多不同的互動情境可納入智慧型3D動畫角色設計的考量。我們提議讓智慧型3D動畫角色在肢體動作表現上具有行動力與表達力的概念，使得動畫角色在互動數位電視系統上，能夠依據不同的情境與角色本身之狀態，選擇適當的動作在螢幕上移動並且能呈現適當的情緒，讓互動數位電視系統之服務更加友善。本研究以JAVA開發動畫系統，並設計實驗驗證不同介面對使用者的影響，結果顯示，使用者認為智慧型3D動畫角色介面是最有善的。 / In recent years, intelligent interactive digital TV is one of the most important applications in the research of digital living space. We think a good interactive TV system must have a vivid user interface to interact with users. In this research, we propose to incorporate intelligent 3D character into the interface design for interactive digital TV system, to enhance the user experience of the interactive digital TV system. In the smart interactive digital TV system we developed before, call SITV, many interactive scenarios can be considered in the design of intelligent 3D character. We propose to develop our intelligent 3D character with the concepts of mobility and expressiveness on body motion such that appropriate emotions can be presented through motions depending on the scenario and character configuration. For example, an intelligent 3D character can act like a housekeeper living in the TV monitor. He can take different actions for different scenarios to make the service friendlier. We have developed our animation system in JAVA and designed experiments to evaluate different types of user interface design on different scenarios. The experimental results show that an interface with an intelligent 3D character will be friendlier than the others.

透過程序方式有效且快速的自動產生出生動的3D電腦動畫，一直以來是該領域中研究人員所追尋的目標。以中國舞獅在梅花樁上的運動為例，用傳統的動畫製作方式，要能在短時間內產生出符合雙人舞獅演員協同運動的限制，並在佈滿不規則梅花樁的場景中搜尋一條可行走的路徑，是相當費時費力的。我們提出了一套動畫產生系統，讓雙人舞獅演員在隨機產生梅花樁的虛擬環境中，透過協同運動的計畫器，搜尋出可行走的路徑。我們的路徑規劃演算法是依據最佳化優先搜尋演算法的精神來建置，最後並以程序的方式自動模擬出行走過程的3D電腦動畫。這些動畫包含梅花樁上常見的表演動作，如跳躍和轉身等。我們的實驗結果顯示，擬真的舞獅跳梅花樁動畫，可以用互動的方式由協同運動計畫器自動產生。

在這個研究中，我們嘗試將節奏的要素（速度、誇張度與時間調配）參數化，以產生能控制特定風格之人物角色的動畫。角色動作風格化的生成及控制是藉由一個層級式的動畫控制系統RhyCAP (Rhythmic Character Animation Playacting system), 透過一個節奏動作控制（Rhythmic Motion Control, RMC) 的方法來實現。RMC是基於傳統動畫的原則，設計參數化的動作指令，來產生生動並具有說服力的角色動作。此外，RMC也提供了運動行為的模型來控制角色動畫的演出。藉由RhyCAP系統所提供的高階控制介面，即使是沒有經過專業傳統動畫技巧訓練的使用者，也能夠創作出戲劇性的中國舞獅動畫。 / In this research, we attempt to parameterize the rhythmic factors (tempo, exaggeration and timing) into the generation of controllable stylistic character animation. The stylized character motions are generated by a hierarchical animation control system, RhyCAP (Rhythmic Character Animation Playacting system) and realized through an RMC (Rhythmic Motion Control) scheme. The RMC scheme can generate convincible and expressive character motions from versatile action commands with the rhythmic parameters defined according to the principles of traditional animation. Besides, RMC also provide controllable behavior models to enact the characters. By using the high-level control interface of the RhyCAP system, the user is able to create a dramatic Chinese Lion Dance animation intuitively even though he may not be professionally trained with traditional animation skills.

NPR(Non-photorealistic Rendering)主要目的是透過不同的演算法，由電腦自動產生各種不同繪畫風格的影像，目前的NPR系統礙於演算法的計算速度，多數都僅針對靜止的單一圖片進行處理，故本研究試圖對二維空間中已發展的NPR演算法做延伸，在空間領域以及MPEG壓縮領域上分別提出不同的加速效能方式。在空間方面針對不同的範圍套用NPR演算法，如臉部、膚色區塊等有意義的部份；而在MPEG壓縮格式上，透過MPEG中的I,P,B-frame不同的特性，視影像中的差異度做不同的套用方式，以求改進NPR演算法效能，達到即時產生NPR特效的影片或動畫，進一步應用於多媒體娛樂以及人機互動機制。 / Recently, various non-photorealistic rendering (NPR) techniques have been developed for computers to generate images of different artistic styles automatically. Due to the complexity of the algorithms, however, most NPR methods are limited to the processing of static images. It is the objective of this thesis to extend and improve existing NPR techniques to enable near real-time processing of video. The enhancement can be achieved in both spatial and compressed domains. In the spatial domain, computational complexity is reduced by applying NPR only to selective regions in the images, e.g., face or skin area. In the MPEG compressed domain, by exploiting the relationship among I, P, and B frames, different strategies can be developed to increase the efficiency of the NPR algorithm. Experimental results have demonstrated the efficacy of the proposed methods and validated the near real-time creation of NPR video effects.