Search

Data-driven character animation techniques rely on the existence of a properly established model of motion, capable of describing its rich context. However, commonly used motion representations often fail to accurately encode the full articulation of motion, or present artifacts. In this work, we address the fundamental problem of finding a robust pose representation for motion modeling, suitable for deep character animation, one that can better constrain poses and faithfully capture nuances correlated with skeletal characteristics. Our representation is based on dual quaternions, the mathematical abstractions with well-defined operations, which simultaneously encode rotational and positional orientation, enabling a hierarchy-aware encoding, centered around the root. We demonstrate that our representation overcomes common motion artifacts, and assess its performance compared to other popular representations. We conduct an ablation study to evaluate the impact of various losses that can be incorporated during learning. Leveraging the fact that our representation implicitly encodes skeletal motion attributes, we train a network on a dataset comprising of skeletons with different proportions, without the need to retarget them first to a universal skeleton, which causes subtle motion elements to be missed. We show that smooth and natural poses can be achieved, paving the way for fascinating applications., Comment: Presented at the ACM SIGGRAPH/Eurographics Symposium on Computer Animation, SCA'22

Direct Delta Mush (DDM) is a high-quality, direct skinning method with a low setup cost. However, its storage and run-time computing cost are relatively high for two reasons: its skinning weights are 4 X 4 matrices instead of scalars like other direct skinning methods, and its computation requires one 3 X 3 Singular Value Decomposition per vertex. In this paper, we introduce a compression method that takes a DDM model and splits it into two layers: the first layer is a smaller DDM model that computes a set of virtual bone transformations and the second layer is a Linear Blend Skinning model that computes per-vertex transformations from the output of the first layer. The two-layer model can approximate the deformation of the original DDM model with significantly lower costs. Our main contribution is a novel problem formulation for the DDM compression based on a continuous example-based technique, in which we minimize the compression error on an uncountable set of example poses. This formulation provides an elegant metric for the compression error and simplifies the problem to the common linear matrix factorization. Our formulation also takes into account the skeleton hierarchy of the model, the bind pose, and the range of motions. In addition, we propose a new update rule to optimize DDM weights of the first layer and a modification to resolve the floating-point cancellation issue of DDM.

In a conventional optical motion capture (MoCap) workflow, two processes are needed to turn captured raw marker sequences into correct skeletal animation sequences. Firstly, various tracking errors present in the markers must be fixed ( cleaning or refining ). Secondly, an agent skeletal mesh must be prepared for the actor/actress, and used to determine skeleton information from the markers ( re-targeting or solving ). The whole process, normally referred to as solving MoCap data, is extremely time-consuming, labor-intensive, and usually the most costly part of animation production. Hence, there is a great demand for automated tools in industry. In this work, we present MoCap-Solver, a production-ready neural solver for optical MoCap data. It can directly produce skeleton sequences and clean marker sequences from raw MoCap markers, without any tedious manual operations. To achieve this goal, our key idea is to make use of neural encoders concerning three key intrinsic components: the template skeleton, marker configuration and motion, and to learn to predict these latent vectors from imperfect marker sequences containing noise and errors. By decoding these components from latent vectors, sequences of clean markers and skeletons can be directly recovered. Moreover, we also provide a novel normalization strategy based on learning a pose-dependent marker reliability function, which greatly improves system robustness. Experimental results demonstrate that our algorithm consistently outperforms the state-of-the-art on both synthetic and real-world datasets.

Iscrtavanje animacija u pogonskom sustavu igara koristeći skeletnu animaciju Proučavaju se sustavi za generiranje skeletne animacije za 2D likove Spine2D i pogonski sustav Unity. Upoznavaju se pojmovi kao kostur, koža, konstrukcija kostura i animacija kostiju, koji se primjenjuju kroz korištenje Spine2D sustava za izradu skeletne animacije lika. Također se upoznaje s korištenjem sustava Unity za izradu pokazne 2D videoigre gdje se koriste kreirane animacije disanja, trčanja, skakanja , napada i zaleta. Pregledom videoigre opisat će se Unity komponente „Collider2D“ i „Rigidbody2D“, izrada likova igrača i protivnika kao i modeliranje logike njihovih pokreta i napada. Displaying animations in game engine using skeletal animation Analysing animation tool for 2D skeletal animation Spine2D and game engine Unity. We are introducing terms such as skeleton, mesh, rigging and skinning, witch are applied trough using Spine2D system for creating characters skeletal animations. Using game engine Unity for creating video 2D videogame where idle, running, jumping, attack and dashing animation are being used. Reviewing the videogame we'll describe Unity components „Collider2D“ and „Rigidbody2D“, creating player and enemy characters as well as their movement and attacking logic.

We apply a skeletal animation technique developed for general computer graphics animation to display the dynamic shape of protein molecules. Polygon-based models for macromolecules such as atomic representations, surface models, and protein ribbon models are deformed by the motion of skeletal bones that provide coarse-grained descriptions of detailed computer graphics models. Using the animation software Blender, we developed methods to generate the skeletal bones for molecules. Our example of the superposition of normal modes demonstrates the thermal fluctuating motion obtained from normal mode analysis. The method is also applied to display the motions of protein molecules using trajectory coordinates of a molecular dynamics simulation. We found that a standard motion capture file was practical and useful for describing the motion of the molecule using available computer graphics tools.

A significant fraction of the world's population have experienced virtual characters through games and movies, and the possibility of online VR social experiences may greatly extend this audience. At present, the skin deformation for interactive and real-time characters is typically computed using geometric skinning methods. These methods are efficient and simple to implement, but obtaining quality results requires considerable manual "rigging" effort involving trial-and-error weight painting, the addition of virtual helper bones, etc. The recently introduced Delta Mush algorithm largely solves this rig authoring problem, but its iterative computational approach has prevented direct adoption in real-time engines. This paper introduces Direct Delta Mush, a new algorithm that simultaneously improves on the efficiency and control of Delta Mush while generalizing previous algorithms. Specifically, we derive a direct rather than iterative algorithm that has the same ballpark computational form as some previous geometric weight blending algorithms. Straightforward variants of the algorithm are then proposed to further optimize computational and storage cost with insignificant quality losses. These variants are equivalent to special cases of several previous skinning algorithms. Our algorithm simultaneously satisfies the goals of reasonable efficiency, quality, and ease of authoring. Further, its explicit decomposition of rotational and translational effects allows independent control over bending versus twisting deformation, as well as a skin sliding effect.

Automatic pose and shape initialization is the first step to conquer the problem of human tracking, acquiring prior knowledge about the tracking subject. It is crucial for accomplishing a successful tracking. In this paper, we present a simple and effective framework to automatically calibrate the human pose and shape by integrating a data driven shape parameterization into the skeletal animation pipeline and optimizing the template body model against multiview silhouette images to acquire the tracking subject shape and pose information. A PCA based approach is proposed to summarize the space of human body variations in height, weight, muscle tone, gender, body shape. Multiview analysis by synthesis optimization in the hierarchial order is employed to realize pose and shape calibration. Finally, experiments on HumanEvaII and Human3.6m dataset demonstrate our approach is very effective and robust to real world situations.

Animating a newly designed character using motion capture (mocap) data is a long standing problem in computer animation. A key consideration is the skeletal structure that should correspond to the available mocap data, and the shape deformation in the joint regions, which often requires a tailored, pose-specific refinement. In this work, we develop a neural technique for articulating 3D characters using enveloping with a pre-defined skeletal structure which produces high quality pose dependent deformations. Our framework learns to rig and skin characters with the same articulation structure (e.g., bipeds or quadrupeds), and builds the desired skeleton hierarchy into the network architecture. Furthermore, we propose neural blend shapes--a set of corrective pose-dependent shapes which improve the deformation quality in the joint regions in order to address the notorious artifacts resulting from standard rigging and skinning. Our system estimates neural blend shapes for input meshes with arbitrary connectivity, as well as weighting coefficients which are conditioned on the input joint rotations. Unlike recent deep learning techniques which supervise the network with ground-truth rigging and skinning parameters, our approach does not assume that the training data has a specific underlying deformation model. Instead, during training, the network observes deformed shapes and learns to infer the corresponding rig, skin and blend shapes using indirect supervision. During inference, we demonstrate that our network generalizes to unseen characters with arbitrary mesh connectivity, including unrigged characters built by 3D artists. Conforming to standard skeletal animation models enables direct plug-and-play in standard animation software, as well as game engines., Comment: SIGGRAPH 2021. Project page: https://peizhuoli.github.io/neural-blend-shapes/ , Video: https://youtu.be/antc20EFh6k

En este ensayo se describen los elementos del desarrollo de un Framework 3D para el motor gráfico GameMaker con el objetivo de construir un juego de estilo acción en tercera persona. Este trabajo requiere la integración en dicho motor pensado para las dos dimensiones, componentes tales como la importación de modelos 3D, las animaciones por esqueleto, la iluminación o las colisiones en un espacio tridimensional. Finalmente buscando la recreación de un viejo proyecto de videojuego con el fin de ejercer una comparación entre las dos versiones con más de seis años de diferencia entre ellas. In this essay, it describes the elements of the development of a 3D Framework for the GameMaker game engine with the objective of building a third person action game. This project requires the integration in the said engine thought for twodimension components such as 3D model importer, skeletal animations, illumination or collisions on a three-dimensional space. Looking for remaking an old proyect of a video game with the purpose of establishing a comparison between the two versions with six years of difference between them. En aquest assaig es descriuen els elements de el desenvolupament d'un Framework 3D per al motor gràfic GameMaker amb l'objectiu de construir un joc d'estil acció en tercera persona. Aquest treball requereix la integració en l'esmentat motor pensat per a les dues dimensions, components com ara la importació de models 3D, les animacions per esquelet, la il·luminació o les col·lisions en un espai tridimensional. Finalment buscant la recreació d'un vell projecte de videojoc per tal d'exercir una comparació entre les dues versions amb més de sis anys de diferència entre elles.

Skeletal animation being one of the most distinct technics in real-time computer graphic is constantly evolving, since the time it was first implemented. New features, methods of synthesis and processing are being actively worked on and shipped in commercial titles. One missing aspect of this subbranch of rendering is proper automatic validation for humanoid movements. In response to that niche a study was prepared. It consisted of typical industry standard animation environment, used state-of-the-art animations resources and run with repeatable results in controlled environment. On these bases motion data for selected animated joints were measured and stored. Collected test data was analyzed against biomechanical constraints of human body. With conclusion of promising results, further research and possible applications were proposed.

With the gradual development of virtual reality (VR) technology, users have increasingly higher demand for system interaction. The human-computer interaction (HMI) by means of data glove is a widely used interaction means in the current days. In this paper, a type of single-chip microcomputer based low cost data glove is designed for figure posture acquisition. Also, a programmable control virtual hand model is designed for simulation. And they are used for building a basic HMI system. In terms of hardware, the system adopts a single-chip microcomputer as the core of data processing and collects, processes and transmits hand posture data together with peripheral data acquisition circuit. In terms of software, mapping is established between the practical and virtual hand postures based on the strap-down navigation algorithm and the 3D skeletal animation algorithm, for the purpose of basic interactive application of data gloves.

Даний дипломний проект присвячений створенню алгоритмічно програмного методу генерації LOD для моделей зі скелетом. Розроблений метод дозволяє спрощувати тривимірні анімовані без суттєвої втрати якості анімації. Це забезпечується перерахунком ваг вершин тривимірної моделі під час прощення. В рамках дипломної роботи також розроблено програмну реалізацію запропонованого методу у вигляді плагіна для рушія Unity, що підтримує створення LOD довільної деталізації на льоту моделей на льоту, використання цих моделей прямо в редакторі, розрахунок помилки цих моделей, та експорт моделей у форматі OBJ. У даній роботі розроблено сам алгоритмічно програмний метод генерації LOD моделей, архітектуру його імплементації та саму імплементації. Результуючі моделі зберігають топологію, мають високу точність анімації, та не мають значних артефактів. This diploma project deals with the development of an algorithmic software method for generation of animated LOD models. Developed method allows for simplification of animated 3d models without a significant loss of animation quality. This is provided by recalculating the weights of vertices of the model during simplification. A software implementation of the proposed method was developed in a form of a plugin for Unity engine , that supports creation of LOD of desired complexity on the fly, use of this models in Unity editor, calculation of error on those models and export of those models to OBJ format. In this work an algorithmic software method, architecture of its implementation and the implementation itself were developed. Resulting models preserve the topology of original model, have high animation quality and don’t have major artifacts.

The animation of articulated characters is a central problem in the computer graphics field. Skeletal animation techniques define a workflow which has proven to be effective for boundary representations (B-Reps). This paper extends the classical skeletal animation pipeline to deal with characters internal tissues. In contrast to most common approaches, the proposed technique automates all the stages of this workflow. Well known skinning algorithms, such as Linear Blending Skinning, Dual Quaternion Skinning or Optimized Centers of Rotation were adapted to allow the use of our technique in applications where interactivity is required. The pipeline proposed in this paper can be used in many computer graphics systems such as games or educational applications to visualize and animate the internal anatomy of a virtual character at interactive rates.

The objective of this paper is to develop a dose assessment method that takes into account the working postures and the non-uniformity of the radiation fields to ensure the radiation safety of workers in nuclear facilities. To simulate different working postures, the working posture models were developed with skeletal animation technology. And to assess the exposure dose to workers in a non-uniform radiation field, virtual reality technology was used to develop a model of a hypothetical human with organ-monitoring-points distributed in his/her organs and tissues. And then a dose assessment method based on skeletal animation technology and the organ-monitoring-points was developed. Simulation results were compared with that of MCNP, the point model and the organ’s minimum bounding box model, and they show that the method is effective in providing dose assessments to workers, taking into consideration the working postures and non-uniformity of radiation environments.

Facial animation is a time-consuming and cumbersome task that requires years of experience and/or a complex and expensive set-up. This becomes an issue, especially when animating the multitude of secondary characters required, e.g. in films or video-games. We address this problem with a novel technique that relies on motion graphs to represent a landmarked database. Separate graphs are created for different facial regions, allowing a reduced memory footprint compared to the original data. The common poses are identified using a Euclidean-based similarity metric and merged into the same node. This process traditionally requires a manually chosen threshold, however, we simplify it by optimizing for the desired graph compression. Motion synthesis occurs by traversing the graph using Dijkstra's algorithm, and coherent noise is introduced by swapping some path nodes with their neighbours. Expression labels, extracted from the database, provide the control mechanism for animation. We present a way of creating facial animation with reduced input that automatically controls timing and pose detail. Our technique easily fits within video-game and crowd animation contexts, allowing the characters to be more expressive with less effort. Furthermore, it provides a starting point for content creators aiming to bring more life into their characters.

In this paper, we propose a generative recurrent model for human-character interaction. Our model is an encoder-recurrent-decoder network. The recurrent network is composed by multiple layers of long short-term memory (LSTM) and is incorporated with an encoder network and a decoder network before and after the recurrent network. With the proposed model, the virtual character's animation is generated on the fly while it interacts with the human player. The coming animation of the character is automatically generated based on the history motion data of both itself and its opponent. We evaluated our model based on both public motion capture databases and our own recorded motion data. Experimental results demonstrate that the LSTM layers can help the character learn a long history of human dynamics to animate itself. In addition, the encoder---decoder networks can significantly improve the stability of the generated animation. This method can automatically animate a virtual character responding to a human player.

We propose a novel motion retargeting method that efficiently estimates artist-friendly rig space parameters. Inspired by the workflow typically observed in keyframe animation, our approach transfe...

Inverse kinematics (IK) equations are usually solved through approximated linearizations or heuristics. These methods lead to character animations that are unnatural looking or unstable because they do not consider both the motion coherence and limits of human joints. In this paper, we present a method based on the formulation of multi-variate Gaussian distribution models (MGDMs), which precisely specify the soft joint constraints of a kinematic skeleton. Each distribution model is described by a covariance matrix and a mean vector representing both the joint limits and the coherence of motion of different limbs. The MGDMs are automatically learned from the motion capture data in a fast and unsupervised process. When the character is animated or posed, a Gaussian process synthesizes a new MGDM for each different vector of target positions, and the corresponding objective function is solved with Jacobian-based IK. This makes our method practical to use and easy to insert into pre-existing animation pipelines. Compared with previous works, our method is more stable and more precise, while also satisfying the anatomical constraints of human limbs. Our method leads to natural and realistic results without sacrificing real-time performance.

The Animation Rigging package for Unity enables users to setup rigs to procedurally control skeletal animations as a post-process. Attendees of this Studio Workshop will get hands-on experience working with this system in step-by-step tutorials. We will also show how to extend the package functionalities using C#.

The widely used ambient occlusion (AO) technique provides an approximation of some global illumination effects and is efficient enough for use in real-time applications. Because it relies on computing the visibility from each point on a surface, AO computation is expensive for dynamically deforming objects, such as characters in particular. In this paper, we describe an algorithm for producing high-quality dynamically changing AO for characters. Our fundamental idea is to factorize the AO computation into a coarse-scale component in which visibility is determined by approximating spheres, and a fine-scale component that leverages a skinning-like algorithm for efficiency, with both components trained in a regression against ground-truth AO values. The resulting algorithm accommodates interactions with external objects and generalizes without requiring carefully constructed training data. Extensive comparisons illustrate the capabilities and advantages of our algorithm.

V diplomski nalogi smo v jeziku C++ s pomočjo algoritma inverzne kinematike FABRIK v kombinaciji s fizikalno knjižnico Bullet Physics implementirali sistem skeletne animacije z dinamično proceduralnim generiranjem animacijskih poz (angl. animation pose) v realnem času. Najprej smo se lotili pregleda tipov animacij v računalniški grafiki in opisali njihove prednosti ter slabosti. Temo smo nato poglobili na implementacijo sistema skeletne animacije. Za tem smo povzeli osnove inverzne kinematike in opisali algoritem FABRIK. S pridobljenim znanjem smo se nato lotili še proceduralne generacije animacij s pomočjo fizikalne knjižnice. Na koncu smo govorili še o sami vizualizaciji poz skeletne animacije in poleg zaznanih problemov opisali še možne izboljšave sistema. In this diploma thesis we used the FABRIK inverse kinematics algorithm in combination with physics library Bullet and C++ programming language to create a skeletal animation system with the ability to generate dynamic and procedural animation poses in real time. At the beginning we talked about different types of animations found in computer graphics and their pros and cons. We then focused on the implementation of the skeletal animation system. After that we talked about inverse kinematics and described the FABRIK algorithm. With the acquired knowledge we then proceeded to procedural generation of body poses with the help of the Bullet physics library. Finally, we talked about the visualization of skeletal animation and in addition to the problems encountered, we also described possible improvements to the entire system.

Optical motion-capture systems can be used to animate characters in real time based on human demonstrations. However, most approaches do not consider the detailed finger movements necessary for object manipulation. The proposed online motion-capture framework encourages natural motions by automatically guiding the avatar's motion toward the desired behavior based on a set of captured reference motions for the same behavior. The proposed motion controller imitates the user's finger and body gestures to enable performance-based animation of human avatars that can manipulate virtual objects in real time.

In 3D character animation, the expressiveness of the motions is very important for the immersion and the perception in a virtual environment. Traditional animation is often superior to show this expressiveness. However, the resulting animation is typically not interactive. We present in this paper an interactive and intuitive method to add expressiveness to avatars by the exaggeration of the characters and their motions. We first use the data from a sensor holding by the user to create a parameterized order. Then this intuitive order is interpreted by the system to drive the exaggeration of the involved limbs and the deformation of the mesh of the avatar. We finally provide a post-exaggeration module adapting the resulting motion to the environment and placing the camera for an optimal perception. Experimental results show that the method can efficiently convert user’s interaction intent to expressive cartoon-style character animation.