Retargetting motion to new characters

Gleicher, Michael

doi:10.1145/280814.280820

Cited by 681 publications

(451 citation statements)

References 15 publications

Supporting

Mentioning

443

Contrasting

Unclassified

Order By: Relevance

“…As a rule, motion retargeting is applied to characters of different sizes in character animation. Gleicher [8] used a space-time constraint solver to apply motions to characters of different body lengths. This method, however, is not suitable for a real-time system.…”

Section: Calibration and Synchronizationmentioning

confidence: 99%

Dance Experience System Using Multiple Kinects

Baek¹,

Kim²

2015

IJFCC

View full text Add to dashboard Cite

Abstract-We present a new method for comparing users' motions captured in real time by multiple Kinect sensors with an expert's movements stored in a DB so as to help users experience and learn how to dance. Recently, lots of experience games where users copy some motions to score have been developed. However, it is difficult to collect users' joint data or to clearly compare movements with one sensor because of blocked body parts and unsuccessful tracking. Therefore, such games cannot be applicable to learning beyond simple in-game experiences. As an alternative, this study proposes a method for using multiple Kinect sensors to combine skeletal data and thus to retrieve motions. Also, we propose a method for directly comparing postures between characters of different body sizes. The direct comparison of postures ensures accuracy as no motion is adapted in the process. The proposed dance experience learning system is suitable for learning how to dance as it is easy to implement, features real-time posture comparison and displays the results of important body parts compared.

show abstract

Section: Calibration and Synchronizationmentioning

confidence: 99%

Dance Experience System Using Multiple Kinects

Baek¹,

Kim²

2015

IJFCC

View full text Add to dashboard Cite

show abstract

“…Retargeting has been an area of much research in the animation community since [9]'s work with uses optimization and low-pass filtering to retarget motion. Many other retargeting algorithms use various approaches: [16] retargets motion by using angular trajectories, and then solve several body areas, [17] uses a hierarchical approach to retargeting, [21] uses an intermediate skeleton and IK to handle retargeting between skeletons with different topologies.…”

Section: Related Workmentioning

confidence: 99%

Automating the Transfer of a Generic Set of Behaviors onto a Virtual Character

Feng

Huang

et al. 2012

Motion in Games

View full text Add to dashboard Cite

Abstract. Humanoid 3D models can be easily acquired through various sources, including online. The use of such models within a game or simulation environment requires human input and intervention in order to associate such a model with a relevant set of motions and control mechanisms. In this paper, we demonstrate a pipeline where humanoid 3D models can be incorporated within seconds into an animation system, and infused with a wide range of capabilities, such as locomotion, object manipulation, gazing, speech synthesis and lip syncing. We offer a set of heuristics that can associated arbitrary joint names with canonical ones, and describe an fast retargeting algorithm that enables us to instill a set of behaviors onto an arbitrary humanoid skeleton. We believe that such a system will vastly increase the use of 3D interactive characters due to the ease that new models can be animated.Keywords: animation, graphics, system, retargetting 1 Motivation 3D characters are commonly seen in video games, feature films, mobile phone applications and web sites. The generation of an expressive 3D characters requires a series of stages to be applied in order to achieve a 3D character performance. Such stages include the generation of a character model, specifying a skeleton for that model, deforming the model according to the movement of the skeleton, applying motion and control algorithms under a framework, and finally instructing the character to perform. Each of these processes requires a different skillset. For example, 3D models are generated by digital modelers or through hardwarebased acquisition, while animators create or apply motion to the characters.Thus, while many high quality assets such as humanoid models or motion capture data can be readily and inexpensively aquired, the integration of such assets into a working 3D character is not automated and requires expert intervention. For example, after motion capture data is acquired, it then needs to be retargetted onto a specific skeleton. An acquired 3D humanoid model needs a skeleton that satisfies the constraints of a real-time game system, and so forth. Modern game engines provide a means to visualize and animate a 3D character, but require assembly by a programmer or game designer. The complexity of animating 3D virtual characters presents an obstacle for the end user, who cannot

show abstract

“…[Gleicher 1998], and can be applied to 2D animation with our method. Here a feature region based tracking method is presented, commonly used in computer vision, to extract the motion of 2D objects in video or an image sequence.…”

Section: Framework and Overviewmentioning

confidence: 99%

“…Most research on motion capture and motion retargeting focuses on 3D animation [Gleicher 1998;Favreau et al 2004;Sand et al 2003]. Many effective algorithms have been developed and benefited applications including computer games and film special effects.…”

Section: D Motion Capture and Retargetingmentioning

confidence: 99%