TL;DR: This system faithfully recovers facial expression dynamics of the user by adapting a blendshape template to an image sequence of recorded expressions using an optimization that integrates feature tracking, optical flow, and shape from shading.
Abstract: We present a complete pipeline for creating fully rigged, personalized 3D facial avatars from hand-held video. Our system faithfully recovers facial expression dynamics of the user by adapting a blendshape template to an image sequence of recorded expressions using an optimization that integrates feature tracking, optical flow, and shape from shading. Fine-scale details such as wrinkles are captured separately in normal maps and ambient occlusion maps. From this user- and expression-specific data, we learn a regressor for on-the-fly detail synthesis during animation to enhance the perceptual realism of the avatars. Our system demonstrates that the use of appropriate reconstruction priors yields compelling face rigs even with a minimalistic acquisition system and limited user assistance. This facilitates a range of new applications in computer animation and consumer-level online communication based on personalized avatars. We present realtime application demos to validate our method.
TL;DR: In this article, a review article provides an overview of the efforts made on tackling this demanding task and discusses how these findings can be synthesized in computer graphics and can be utilized in the domains of Human-Robot Interaction and Human-Computer Interaction for allowing humans to interact with virtual agents and other artificial entities.
Abstract: A person's emotions and state of mind are apparent in their face and eyes. As a Latin proverb states: 'The face is the portrait of the mind; the eyes, its informers'. This presents a significant challenge for Computer Graphics researchers who generate artificial entities that aim to replicate the movement and appearance of the human eye, which is so important in human-human interactions. This review article provides an overview of the efforts made on tackling this demanding task. As with many topics in computer graphics, a cross-disciplinary approach is required to fully understand the workings of the eye in the transmission of information to the user. We begin with a discussion of the movement of the eyeballs, eyelids and the head from a physiological perspective and how these movements can be modelled, rendered and animated in computer graphics applications. Furthermore, we present recent research from psychology and sociology that seeks to understand higher level behaviours, such as attention and eye gaze, during the expression of emotion or during conversation. We discuss how these findings are synthesized in computer graphics and can be utilized in the domains of Human-Robot Interaction and Human-Computer Interaction for allowing humans to interact with virtual agents and other artificial entities. We conclude with a summary of guidelines for animating the eye and head from the perspective of a character animator.
TL;DR: This volume presents novel computational models for representing digital humans and their interactions with other virtual characters and meaningful environments and describes efficient algorithms to animate, control, and author human-like agents having their own set of unique capabilities, personalities, and desires.
Abstract: This volume presents novel computational models for representing digital humans and their interactions with other virtual characters and meaningful environments. In this context, we describe efficient algorithms to animate, control, and author human-like agents having their own set of unique capabilities, personalities, and desires. We begin with the lowest level of footstep determination to steer agents in collision-free paths. Steering choices are controlled by navigation in complex environments, including multi-domain planning with dynamically changing situations. Virtual agents are given perceptual capabilities analogous to those of real people, including sound perception, multi-sense attention, and understanding of environment semantics which affect their behavior choices. The roles and impacts of individual attributes, such as memory and personality are explored. The animation challenges of integrating a number of simultaneous behavior and movement demands on an agent are addressed through an open source software system. Finally, the creation of stories and narratives with groups of agents subject to planning and environmental constraints culminates the presentation.
TL;DR: This paper proposes a data-driven-based robust human motion denoising approach by mining the spatial-temporal patterns and the structural sparsity embedded in motion data by replacing the regularly used entire pose model with a much fine-grained partlet model as feature representation to exploit the abundant local body part posture and movement similarities.
Abstract: Motion capture is an important technique with a wide range of applications in areas such as computer vision, computer animation, film production, and medical rehabilitation. Even with the professional motion capture systems, the acquired raw data mostly contain inevitable noises and outliers. To denoise the data, numerous methods have been developed, while this problem still remains a challenge due to the high complexity of human motion and the diversity of real-life situations. In this paper, we propose a data-driven-based robust human motion denoising approach by mining the spatial-temporal patterns and the structural sparsity embedded in motion data. We first replace the regularly used entire pose model with a much fine-grained partlet model as feature representation to exploit the abundant local body part posture and movement similarities. Then, a robust dictionary learning algorithm is proposed to learn multiple compact and representative motion dictionaries from the training data in parallel. Finally, we reformulate the human motion denoising problem as a robust structured sparse coding problem in which both the noise distribution information and the temporal smoothness property of human motion have been jointly taken into account. Compared with several state-of-the-art motion denoising methods on both the synthetic and real noisy motion data, our method consistently yields better performance than its counterparts. The outputs of our approach are much more stable than that of the others. In addition, it is much easier to setup the training dataset of our method than that of the other data-driven-based methods.
TL;DR: In this paper, a framework for shape analysis of curves in Lie groups for problems of computer animations is developed, which can be used to find cyclic approximations of non-cyclic character animations and interpolate between existing animations.
Abstract: Shape analysis methods have in the past few years become very popular, both for theoretical exploration as well as from an application point of view Originally developed for planar curves, these methods have been expanded to higher dimensional curves, surfaces, activities, character motions and many other objects In this paper, we develop a framework for shape analysis of curves in Lie groups for problems of computer animations In particular, we will use these methods to find cyclic approximations of non-cyclic character animations and interpolate between existing animations to generate new ones
TL;DR: A number of ways in which 3D animation software can play a valuable role in visualizing and communicating macromolecular structures and dynamics are discussed.
TL;DR: A general, real-time solution to the inversion of the rig function - the function which maps animation data from a character's rig to its skeleton, which greatly improves the productivity of 3D animation, while retaining the flexibility and creativity of artistic input is proposed.
Abstract: We propose a general, real-time solution to the inversion of the rig function - the function which maps animation data from a character's rig to its skeleton. Animators design character movements in the space of an animation rig, and a lack of a general solution for mapping motions from the skeleton space to the rig space keeps the animators away from the state-of-the-art character animation methods, such as those seen in motion editing and synthesis. Our solution is to use non-linear regression on sparse example animation sequences constructed by the animators, to learn such a mapping offline. When new example motions are provided in the skeleton space, the learned mapping is used to estimate the rig space values that reproduce such a motion. In order to further improve the precision, we also learn the derivative of the mapping, such that the movements can be fine-tuned to exactly follow the given motion. We test and present our system through examples including full-body character models, facial models and deformable surfaces. With our system, animators have the freedom to attach any motion synthesis algorithms to an arbitrary rigging and animation pipeline, for immediate editing. This greatly improves the productivity of 3D animation, while retaining the flexibility and creativity of artistic input.
TL;DR: In this paper, a multi-frame regressor is configured to map information descriptive of facial expressions depicted in two or more images to information describing a single avatar blend shape, which is used to generate high quality, real-time avatar animation.
Abstract: Avatar animation systems disclosed herein provide high quality, real-time avatar animation that is based on the varying countenance of a human face. In some example embodiments, the real-time provision of high quality avatar animation is enabled at least in part, by a multi-frame regressor that is configured to map information descriptive of facial expressions depicted in two or more images to information descriptive of a single avatar blend shape. The two or more images may be temporally sequential images. This multi-frame regressor implements a machine learning component that generates the high quality avatar animation from information descriptive of a subject's face and/or information descriptive of avatar animation frames previously generated by the multi-frame regressor. The machine learning component may be trained using a set of training images that depict human facial expressions and avatar animation authored by professional animators to reflect facial expressions depicted in the set of training images.
TL;DR: In this paper, Stereoscopic Illusions are used in 3D Cinema of Attractions and CG Animation to create new realisms and depth and emergence constructions for CG animation.
Abstract: List of Figures Preface Acknowledgements Introduction: Stereoscopic Illusions 1. Hyper-haptic Visuality 2. 3D Cinema of Attractions 3. New Realisms 4. Depth and Emergence Constructions 5. Arresting Forms 6. Bodies in Motion 7. CG Animation Conclusion Bibliography
TL;DR: This work proposes skeleton abstraction and motion retargeting algorithms for finding correspondences and transferring motion between skeletons, or portions of skeletons, with varied topology, for interleaved modeling and animation creation and editing.
Abstract: We introduce AniMesh, a system that supports interleaved modeling and animation creation and editing. AniMesh is suitable for rapid prototyping and easily accessible to non-experts. Source animations can be obtained from commodity motion capture devices or by adapting canned motion sequences. We propose skeleton abstraction and motion retargeting algorithms for finding correspondences and transferring motion between skeletons, or portions of skeletons, with varied topology. Motion can be copied-and-pasted between kinematic chains with different skeletal topologies, and entire model parts can be cut and reattached, while always retaining plausible, composite animations.
TL;DR: A fast and robust local motion planning algorithm is introduced to solve the Boundary Value Problem on an energy graph to generate motions that could only previously be computed by global planning methods.
Abstract: In this paper, we present a local motion planning algorithm for character animation. We focus on motion planning between two distant postures where linear interpolation leads to penetrations. Our framework has two stages. The motion planning problem is first solved as a Boundary Value Problem (BVP) on an energy graph which encodes penetrations, motion smoothness and user control. Having established a mapping from the configuration space to the energy graph, a fast and robust local motion planning algorithm is introduced to solve the BVP to generate motions that could only previously be computed by global planning methods. In the second stage, a projection of the solution motion onto a constraint manifold is proposed for more user control. Our method can be integrated into current keyframing techniques. It also has potential applications in motion planning problems in robotics.
TL;DR: To enhance the understandability, three popular RaaS services have been classified and verified according to the proposed tree-structured taxonomy of services.
TL;DR: This design and research intervention demonstrates that the combination of technologies, activities, and teacher support can lead to improvements in some of the foundations associated with students’ modeling.
Abstract: Biomechanics, and specifically the biomechanics associated with human movement, is a potentially rich backdrop against which educators can design innovative science teaching and learning activities. Moreover, the use of technologies associated with biomechanics research, such as high-speed cameras that can produce high-quality slow-motion video, can be deployed in such a way to support students’ participation in practices of scientific modeling. As participants in classroom design experiment, fifteen fifth-grade students worked with high-speed cameras and stop-motion animation software (SAM Animation) over several days to produce dynamic models of motion and body movement. The designed series of learning activities involved iterative cycles of animation creation and critique and use of various depictive materials. Subsequent analysis of flipbooks of human jumping movements created by the students at the beginning and end of the unit revealed a significant improvement in both the epistemic fidelity of students’ representations. Excerpts from classroom observations highlight the role that the teacher plays in supporting students’ thoughtful reflection of and attention to slow-motion video. In total, this design and research intervention demonstrates that the combination of technologies, activities, and teacher support can lead to improvements in some of the foundations associated with students’ modeling.
TL;DR: This paper proposes a novel stable and fast particle method to couple predictive–corrective incompressible smoothed particle hydrodynamics and geometric lattice shape matching (LSM), which animates the visually realistic interaction of fluids and deformable solids allowing larger time steps or velocity differences.
Abstract: The solid boundary handling has been a research focus in physically based fluid animation. In this paper, we propose a novel stable and fast particle method to couple predictive-corrective incompressible smoothed particle hydrodynamics and geometric lattice shape matching LSM, which animates the visually realistic interaction of fluids and deformable solids allowing larger time steps or velocity differences. By combining the boundary particles sampled from solids with a momentum-conserving velocity-position correction scheme, our approach can alleviate the particle deficiency issues and prevent the penetration artefacts at the fluid-solid interfaces simultaneously. We further simulate the stable deformation and melting of solid objects coupled to smoothed particle hydrodynamics fluids based on a highly extended LSM model. In order to improve the time performance of each time step, we entirely implement the unified particle framework on GPUs using compute unified device architecture. The advantages of our two-way fluid-solid coupling method in computer animation are demonstrated via several virtual scenarios.
TL;DR: This work proposes a new idea to transform complex motion data into RGB images and compare them by content-based image retrieval methods, seeing these images not only as human-understandable visualization of motion characteristics e.g., speed, duration and movement repetition, but also as descriptive features for their ability to preserve key aspects of performed motions.
Abstract: The rapid development of motion capturing technologies has caused a massive usage of human motion data in a variety of fields, such as computer animation, gaming industry, medicine, sports and security. These technologies produce large volumes of complex spatio-temporal data which need to be effectively compared on the basis of similarity. In contrast to a traditional way of extracting numerical features, we propose a new idea to transform complex motion data into RGB images and compare them by content-based image retrieval methods. We see these images not only as human-understandable visualization of motion characteristics e.g., speed, duration and movement repetitions, but also as descriptive features for their ability to preserve key aspects of performed motions. To demonstrate the usability of this idea, we evaluate a preliminary experiment that classifies 1,i¾?034 motions into 14 categories with the $$87.4\,\%$$ precision.
TL;DR: A novel sketch-based human motion retrieval method via selected 2-dimensional (2D) Geometric Posture Descriptor (2GPD) is presented, effective in encoding the 2D posture similarity by exploiting the geometric relationships among different human body parts.
TL;DR: This paper presents a sketch-based approach to direct manipulation interfaces, inspired by artists’ brush painting on canvas, that can be used with any blendshape facial model and allows producing expeditious manipulation in an intuitive way.
Abstract: The blendshape approach is a widely used technique to generate realistic facial animation. However, creating blendshape facial animations using traditional weight editing tools requires either memorizing the function of a large number of parameters, or a trial-and-error search in a high-dimensional space. Direct manipulation interfaces address this problem, allowing the artist to directly move and pin manipulators placed on the surface of the face. Placing manipulators is an open-ended and slightly unnatural task for artists however. In this paper we present a sketch-based approach to this problem, inspired by artists’ brush painting on canvas. In this approach the artist simply sketches directly onto the 3D model the positions of the manipulators that they feel are needed to produce particular facial expression. The manipulators activate the blendshapes in the model and allow the user to interactively create the desired facial poses by a dragging operation in screen coordinates. Our hybrid method can be used with any blendshape facial model and allows producing expeditious manipulation in an intuitive way.
TL;DR: A mathematical framework that allows us to treat character animations as points on infinite-dimensional Hilbert manifolds, and how geodesic paths can be used to calculate interpolations between various animations in a computationally stable way is formulated.
Abstract: In this article, we will formulate a mathematical framework that allows us to treat character animations as points on infinite-dimensional Hilbert manifolds. Constructing geodesic paths between animations on those manifolds allows us to derive a distance function to measure similarities of different motions. This approach is derived from the field of geometric shape analysis, where such formalisms have been used to facilitate object recognition tasks. Analogously to the idea of shape spaces, we construct motion spaces consisting of equivalence classes of animations under reparametrizations. Especially cyclic motions can be represented elegantly in this framework. We demonstrate the suitability of this approach in multiple applications in the field of computer animation. First, we show how visual artefacts in cyclic animations can be removed by applying a computationally efficient manifold projection method. We next highlight how geodesic paths can be used to calculate interpolations between various animations in a computationally stable way. Finally, we show how the same mathematical framework can be used to perform cluster analysis on large motion capture databases, which can be used for or as part of motion retrieval problems.
TL;DR: This thesis introduces a novel optimization-based approach for automatically creating well-edited movies from a 3D animation, and proposes an efficient solution through dynamic programming, by relying on a plausible semi-Markov assumption.
Abstract: The wide availability of high-resolution 3D models and the facility to create new geometrical and animated content, using low-cost input devices, open to many the possibility of becoming digital 3D storytellers. To date there is however a clear lack of accessible tools to easily create the cinematography (positioning and moving the cameras to create shots) and perform the editing of such stories (selecting appropriate cuts between the shots created by the cameras). Creating a movie requires the knowledge of a significant amount of empirical rules and established conventions. Most 3D animation packages do not encompass this expertise, calling the need for automatic approaches that would, at least partially, support users in their creative process. In this thesis we address both challenges of automating cinematography and editing in virtual environments.Using cameras to convey events and actions in dynamic environments is a major concern in many CG applications.In the context of crowd simulation, we present a novel approach to address the challenge of controlling multiple cameras tracking groups of targets. In this first contribution we propose a system that relies on Reynolds' model of steering behaviors to control and locally coordinate a collection of autonomous camera agents evolving in the dynamic 3D environments to shot multi-scale events.Editing a movie is a complex and tedious endeavor that requires a lot of expertise in the field. Therefore, automating the process calls for a formalization of this knowledge. Using continuity editing -- the predominant style of editing -- as a benchmark for evaluating edits, we introduce a novel optimization-based approach for automatically creating well-edited movies from a 3D animation. We propose an efficient solution through dynamic programming, by relying on a plausible semi-Markov assumption.Building upon our first contribution we then propose a novel importance-driven approach to cinematic replay that exploits both the narrative and geometric information in games to automatically compute camera paths. Combined with our editing framework, our solution generates coherent cinematic replays of game sessions.Finally, drawing inspiration from standard practices in the movie industry, we introduce a novel approach to camera path planning. This solution ensures realistic trajectories by constraining camera motion on a virtual rail. The camera position and orientation are optimized in time along the rail to best satisfy visual properties. The computed shots constitute relevant inputs for the editing framework which then generates compelling cinematographic content.
TL;DR: A multi-facet 3D avatar and an animation system for Sinhala Sign language (SSL) which supports the definition and animation of sign gestures without video sequencing or motion capture hardware is presented.
Abstract: A sign language possesses multi-posture and single posture signs that require animation of bones on demand in a 3D signing avatar. Fingerprinting is used for representing unknown words character by character. Ordering and sequencing of signs corresponding to the words/phrases of a natural language are the most essential features of animating a sign language. This paper presents a multi-facet 3D avatar and an animation system for Sinhala Sign language (SSL) which supports the definition and animation of sign gestures without video sequencing or motion capture hardware. The animation system animates upper body of the avatar and consists of 29 bones per arm. Speed and uniformity of the sign gesture animation is achieved by automatically calculating the intermediate and transitional sequences of arm movements of signs within a given number of frames, or with a user defined displacement value per bone. Avatar animation system also supports the definition of fingerprinting signs, with a user defined tag set corresponding to the alphabet of any given sign language. Presented prototype consists of 200 known signs and 40 fingerprinting signs of SSL defined in its sign database and having the capability of animating any sentence in Sinhala language in SSL.
TL;DR: In this article, an interaction education method and system based on the natural image recognition and reality augmentation technology is presented, in which natural image objects in reality are scanned through a camera of an intelligent mobile terminal, the camera transmits images into a pre-school education system, the system calls 3D animation matched with the recognized objects from a database after recognizing codes of the natural recognition objects, the animation is output from a screen of the intelligent mobile terminals, learners can see images obtained by combining scenes shot in real time with virtual 3D animations, and the animation in the images
Abstract: The invention provides an interaction education method and system based on the natural image recognition and reality augmentation technology. Natural image recognition objects in reality are scanned through a camera of an intelligent mobile terminal, the camera transmits images into a pre-school education system, the pre-school education system calls 3D animation matched with the recognized objects from a database after recognizing codes of the natural recognition objects, the animation is output from a screen of the intelligent mobile terminal, learners can see images obtained by combining scenes shot in real time with virtual 3D animation, and the animation in the images can interact with the learners through various games. By means of natural image recognition, the recognition speed is higher, recognition is more stable, and learning is more interesting; the interaction education method and system have the advantages that the natural image recognition is adopted, the interaction property is achieved, and the intelligent mobile terminal can be more conveniently used.
TL;DR: This work uses a blendshape-based synthesis technique that learns the mapping between marker positions and blendshape weights, and calculates the reconstruction error of various animated sequences created from the considered set of markers in comparison to ground truth data.
Abstract: We seek to determine an optimal set of markers for marker-based facial motion capture and animation control. The problem is addressed in two different ways: on the one hand, different sets of empirical markers classically used in computer animation are evaluated; on the other hand, a clustering method that automatically determines optimal marker sets is proposed and compared with the empirical marker sets. To evaluate the quality of a set of markers, we use a blendshape-based synthesis technique that learns the mapping between marker positions and blendshape weights, and we calculate the reconstruction error of various animated sequences created from the considered set of markers in comparison to ground truth data. Our results show that the clustering method outperforms the heuristic approach.
TL;DR: Motion comics typically appropriate the narrative and static artwork of a comic book, which is then manipulated by animation software such as Adobe's After Effects to create an impression that is similar to paper-cut animation as mentioned in this paper.
Abstract: This paper examines the recent emergence of the motion comic as part of a growing relationship between comic books, animation and new forms of digital entertainment and distribution. Motion comics typically appropriate the narrative and ‘static’ artwork of a comic book, which is then manipulated by animation software such as Adobe’s After Effects to create an impression that is similar to paper-cut animation. Early examples of the motion comic form include the episodic web-based Broken Saints (Burgess 2001-2003), as well as Saw: Rebirth (Shuter and Viney 2005). This paper will reveal a number of motion comic aesthetics via a brief analysis of Watchmen (Moore and Gibbons 1986) (Motion Comic Director: Hughes 2008). A number of interactive digital comic narratives are also explored, including Pocom (Emerl.com 2013) and an overview of the ‘App’-based title CIA: Operation Ajax (Burwen et al. 2011).
TL;DR: This work proposes quantification methods for the properties of surface tension models in particle-based fluid simulation systems using smoothed particle hydrodynamics (SPH) and presents a simple modification to improve the quality of inter-particle force models.
Abstract: In this document, we provide additional images and plots to the main paper. First, images of the equilibrium state of benchmark 1 (drop formation) are shown for all surface tension models presented in Sec. 3 in the main paper, combined with different SPH methods (IISPH [ICS∗14], PCISPH [SP09], and WCSPH [BT07]). Further, individual plots for velocities, surface tension forces, and pressure forces that are shown as aggregated values in Sec. 6 of the main paper, are given. At last, velocity plots for benchmark 2 (liquid crown) applied to the mentioned surface tension models in combination with IISPH and WCSPH are given.
TL;DR: The article discusses the role of computer animation in the teaching process and the examples of applications using computer animation and supporting the teach process of technical subjects.
Abstract: Computer animation has a positive effect on memorizing knowledge by students. Used in the process of teaching of technical subjects, it is conductive to the development of mind. Animation allows to familiarize the students with the schemes of solving technical problems and shows the mode of operation of machinery and equipment. In the technique, animations are used, inter alia, in the processes of designing, engineering calculations, visualisation and monitoring technological processes and visualisation of assembly processes. The article discusses the role of computer animation in the teaching process and the examples of applications using computer animation and supporting the teaching process of technical subjects. Selected examples of technical processes in both computer-aided design and manufacturing programs as well as in graphics and animation programs are presented.
TL;DR: A control architecture is presented that generates highly adaptive predictive full-body movements for reaching while walking with highly human-like appearance that is highly robust, even in presence of strong perturbations that require the insertion of additional steps online in order to accomplish the desired task.
Abstract: The planning of human body movements is highly predictive. Within a sequence of actions, the anticipation of a
final task goal modulates the individual actions within the overall pattern of motion. An example is a sequence of
steps, which is coordinated with the grasping of an object at the end of the step sequence. Opposed to this property
of natural human movements, real-time animation systems in computer graphics often model complex activities by
a sequential concatenation of individual pre-stored movements, where only the movement before accomplishing
the goal is adapted. We present a learning-based technique that models the highly adaptive predictive movement
coordination in humans, illustrated for the example of the coordination of walking and reaching. The proposed
system for the real-time synthesis of human movements models complex activities by a sequential concatenation
of movements, which are approximated by the superposition of kinematic primitives that have been learned from
trajectory data by anechoic demixing, using a step-wise regression approach. The kinematic primitives are then
approximated by stable solutions of nonlinear dynamical systems (dynamic primitives) that can be embedded
in control architectures. We present a control architecture that generates highly adaptive predictive full-body
movements for reaching while walking with highly human-like appearance. We demonstrate that the generated
behavior is highly robust, even in presence of strong perturbations that require the insertion of additional steps
online in order to accomplish the desired task.
TL;DR: An animation to animate don’t drink drive case using 3D modeling and a human model is drunk with the surrounding of buildings and trees, sits in car and met with accident after striking with the trees.
Abstract: A 3D human model, car, building, trees are developed using blender, make Human, lightwave and 3Dstudio. Aim of the paper is to animate don’t drink drive case using 3D modeling. A human model is drunk with the surrounding of buildings and trees, sits in car and met with accident after striking with the trees. This paper gives message not to drink while driving. An animation is developed open source python based blender and human model is developed using make Human and is utilize by blender software and objects are used by blender as it supports all types of format like lwo,bvh,3ds,mhx,c3d,c4d and the animation consist of 168 frames with timeline of 10 seconds.
TL;DR: An automatic system to animate a 3D character with human motion streamed from a single video camera that does not need explicit mesh positioning and demonstrates promising performance on par with state-of-the-art techniques.
Abstract: 3D character with human motion offers a high end technology for creating compelling contents in graphics. In this paper, we present an automatic system to animate a 3D character with human motion streamed from a single video camera. The traditional mesh animation process is laborious and requires high skills from the users. To mitigate this limitation, a new way for bringing 3D objects to life is introduced that does not need explicit mesh positioning. In our framework, the animation is driven by the captured motion from an ordinary RGB camera. In order to reduce the ambiguity of the estimated 3D pose, a modified spatio-temporal constraint based algorithm is used for articulated gesture estimation across frames while maintaining temporal coherence. Our approach demonstrates promising performance on par with state-of-the-art techniques. We believe the presented animation system will allow a new audience of novice users to easily and efficiently create animation for arbitrary 3D characters.
TL;DR: The proposed action database is applied to recognizing a video containing a performer doing a specific action and to recovering all the joint angles from the video, and the results show that the database is suitable for this purpose.
Abstract: Understanding human behaviors and generating human-like motions are key technologies for human-robot interaction, motion synthesis in computer animation, sports training, and rehabilitation. Motion capture systems have been developed to accomplish this, and marker-based motion capture systems, in particular, have been used in measuring human actions and performing action recognition. However, marker-based motion capture systems have several drawbacks; in particular, the capture system is expensive, intrusive, and complex to use. Markerless motion capture systems have the potential to overcome these drawbacks. Recently, databases containing a large number of configurations of human whole body actions are available, and they are expected to be reused as new approaches to recognizing actions and recovering action configurations from motion depicted in videos comprising monocular images. This paper describes a design of an action database that consists of action configurations, pose descriptors from silhouett...
TL;DR: A system that automatically generates short choreographies by combining a basic motion with multiple body-part motions using 3D motion data acquired by motion capture is developed.
Abstract: This paper describes a system for supporting the creation of contemporary dance choreography using 3D motion data acquired by motion capture. We developed a system that automatically generates short choreographies by combining a basic motion with multiple body-part motions. The generated choreographies are simulated in 3D animation. It runs on a tablet, so users can select a basic motion and body-part categories by touch operations. The motions are selected and synthesized to the base motion at random timing. To reduce the partial motion synthesis and increase the variety of the generated choreographies, the synthesis timing is adjusted. We experimentally evaluated the effectiveness of our system with eight dancers. From questionnaire results gathered after the experiment, we received many comments about the effectiveness for creation of dance, training of dance techniques, and understanding of dance movements.