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.

Various research has shown the potential and robustness of deep learning-based approaches to synthesise novel motions of 3D characters in virtual environments, such as video games and films. The models are trained with the motion data that is bound to the respective character skeleton (rig). It inflicts a limitation on the scalability and the applicability of the models since they can only learn motions from one particular rig (domain) and produce motions in that domain only. Transfer learning techniques can be used to overcome this issue and allow the models to better adapt to other domains with limited data. This work presents a study of three transfer learning techniques for the proposed Objective-driven motion generation model (OMG), which is a model for procedurally generating animations conditioned on positional and rotational objectives. Three transfer learning approaches for achieving rig-agnostic encoding (RAE) are proposed and experimented with: Feature encoding (FE), Feature clustering (FC) and Feature selection (FS), to improve the learning of the model on new domains with limited data. All three approaches demonstrate significant improvement in both the performance and the visual quality of the generated animations, when compared to the vanilla performance. The empirical results indicate that the FE and the FC approaches yield better transferring quality than the FS approach. It is inconclusive which of them performs better, but the FE approach is more computationally efficient, which makes it the more favourable choice for real-time applications. / Många studier har visat potentialen och robustheten av djupinlärningbaserade modeller för syntetisering av nya rörelse för 3D karaktärer i virtuell miljö, som datorspel och filmer. Modellerna är tränade med rörelse data som är bunden till de respektive karaktärskeletten (rig). Det begränsar skalbarheten och tillämpningsmöjligheten av modellerna, eftersom de bara kan lära sig av data från en specifik rig (domän) och därmed bara kan generera animationer i den domänen. Kunskapsöverföringsteknik (transfer learning techniques) kan användas för att överkomma denna begränsning och underlättar anpassningen av modeller på nya domäner med begränsade data. I denna avhandling presenteras en studie av tre kunskapsöverföringsmetoder för den föreslagna måldriven animationgenereringsnätverk (OMG), som är ett neural nätverk-baserad modell för att procedurellt generera animationer baserade på positionsmål och rotationsmål. Tre metoder för att uppnå rig-agnostisk kodning är presenterade och experimenterade: Feature encoding (FE), Feature clustering (FC) and Feature selection (FS), för att förbättra modellens lärande på nya domäner med begränsade data. All tre metoderna visar signifikant förbättring på både prestandan och den visuella kvaliteten av de skapade animationerna, i jämförelse med den vanilla prestandan. De empiriska resultaten indikerar att både FE och FC metoderna ger bättre överföringskvalitet än FS metoden. Det går inte att avgöra vilken av de presterar bättre, men FE metoden är mer beräkningseffektiv, vilket är fördelaktigt för real-time applikationer.

[pt] Nosso trabalho apresenta uma técnica capaz de gerar animações para personagens virtuais. A inspiração desta técnica vem de vários princípios encontrados na biologia, em particular os conceitos de evolução e seleção natural. Os personagens virtuais, por sua vez, são modelados como criaturas semelhantes a animais, com um sistema locomotor capaz de movimentar seus corpos através de princípios simples da física, tais como forças e torques. Como nossa técnica não depende de nenhum pressuposto sobre a estrutura do personagem, é possível gerar animações para qualquer tipo de criatura virtual. / [en] We present a technique for automatically generating animations for virtual characters. The technique is inspired by several biological principles, especially evolution and natural selection. The virtual characters themselves are modeled as animal-like creatures, with a musculoskeletal system that is capable of moving their bodies through simple physics principles, such as forces and torques. Because our technique does not make any assumptions about the structure of the character, it is capable of generating animations for any kind of virtual creature.