Real-time motion retargeting to highly varied user-created morphologies

Hecker, C.A.; Raabe, Bernd; Enslow, Ryan W.; DeWeese, John; Maynard, Jordan; Prooijen, Kees van

doi:10.1145/1360612.1360626

Cited by 135 publications

(57 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Motion retargeting was then considered as solving kinematic constraints on joint positions and ensuring continuity using displacement maps [Choi and Ko 2000;Gleicher 1998;Lee and Shin 1999]. Another approach consists in defining a morphology-independent representation [Hecker et al 2008; with efficient constraint solvers , or in using an intermediate skeleton [Monzani et al 2000].…”

Section: Skeletal Motion Retargetingmentioning

confidence: 99%

Contact Preserving Shape Transfer For Rigging-Free Motion Retargeting

Basset

Wuhrer

Boyer

et al. 2019

Motion, Interaction and Games

View full text Add to dashboard Cite

Retargeting a motion from a source to a target character is an important problem in computer animation, as it allows to reuse existing rigged databases or transfer motion capture to virtual characters. Surface based pose transfer is a promising approach to avoid the trial-and-error process when controlling the joint angles. The main contribution of this paper is to investigate whether shape transfer instead of pose transfer would better preserve the original contextual meaning of the source pose. To this end, we propose an optimization-based method to deform the source shape+pose using three main energy functions: similarity to the target shape, body part volume preservation, and collision management (preserve existing contacts and prevent penetrations). The results show that our method is able to retarget complex poses, including several contacts, to very different morphologies. In particular, we introduce new contacts that are linked to the change in morphology, and which would be difficult to obtain with previous works based on pose transfer that aim at distance preservation between body parts. These preliminary results are encouraging and open several perspectives, such as decreasing computation time, and better understanding how to model pose and shape constraints. CCS CONCEPTS • Computing methodologies → Animation.

show abstract

Section: Skeletal Motion Retargetingmentioning

confidence: 99%

Contact Preserving Shape Transfer For Rigging-Free Motion Retargeting

Basset

Wuhrer

Boyer

et al. 2019

Motion, Interaction and Games

View full text Add to dashboard Cite

show abstract

“…However, self-interaction constraints are not taken into account. On the other hand, motion retargeting is generally an offline process performed by animators in a desktop environment where constraints are scripted, hence known in advance [3], [14], [15], [16], [17]. The animator can explore the design space by trial and error until a satisfactory motion transfer is obtained on the target character.…”

Section: Related Workmentioning

confidence: 99%

Egocentric Mapping of Body Surface Constraints

Molla

Debarba

Boulic

2018

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

The relative location of human body parts often materializes the semantics of on-going actions, intentions and even emotions expressed, or performed, by a human being. However, traditional methods of performance animation fail to correctly and automatically map the semantics of performer postures involving self-body contacts onto characters with different sizes and proportions. Our method proposes an egocentric normalization of the body-part relative distances to preserve the consistency of self contacts for a large variety of human-like target characters. Egocentric coordinates are character independent and encode the whole posture space, i.e., it ensures the continuity of the motion with and without self-contacts. We can transfer classes of complex postures involving multiple interacting limb segments by preserving their spatial order without depending on temporal coherence. The mapping process exploits a low-cost constraint relaxation technique relying on analytic inverse kinematics; thus, we can achieve online performance animation. We demonstrate our approach on a variety of characters and compare it with the state of the art in online retargeting with a user study. Overall, our method performs better than the state of the art, especially when the proportions of the animated character deviate from those of the performer.

show abstract

“…For indirect mapping, it requires to select features and map them to another character rig with different structure. Hecker et al proposed to pre‐record skeletal motions and map them to specific characters with different morphologies. Lockwood and Singh used finger touches to generate motion data to control leg movements.…”

Section: Related Workmentioning

confidence: 99%

Interactive authoring of bending and twisting motions of short plants using hand gestures

Chen

Johan

2017

Computer Animation & Virtual

View full text Add to dashboard Cite

In this paper, we propose an approach to interactively author the bending and twisting motions of short plants using hand gestures, especially suitable for grass, flowers, and leaves. Our method is based on the observations that hand motions can represent the bending and twisting motions of short plants and using a hand to describe motions is natural and proficient for human. We therefore use a hand as a "puppet" to author the animation of one single short plant based on transferring the motions of a hand to the motions of a short plant. We first author the global motions of the short plant followed by the motions of its elements such as leaves and flowers. We also propose a framework to utilize the animation results to animate a field of short plants and further adjust the motion effects according to the properties of the short plants, such as rigidity. As a result, users can intuitively and rapidly author and generate their desired motions of short plants under the influence of external forces. Especially, our method is accessible to non-expert users and suitable for fast prototyping and authoring specific motions of short plants such as in cartoons.

show abstract

Real-time motion retargeting to highly varied user-created morphologies

Cited by 135 publications

References 30 publications

Contact Preserving Shape Transfer For Rigging-Free Motion Retargeting

Contact Preserving Shape Transfer For Rigging-Free Motion Retargeting

Egocentric Mapping of Body Surface Constraints

Interactive authoring of bending and twisting motions of short plants using hand gestures

Contact Info

Product

Resources

About