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

Feng, Andrew; Huang, Yazhou; Xu, Yaowu; Shapiro, Ari

doi:10.1007/978-3-642-34710-8_13

Cited by 13 publications

(6 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In their physically-based motion retargeting filter, Tak and Ko [2005] make use of dynamics constraints to achieve physically plausible motions. Feng et al [2012] proposed heuristics that can map arbitrary joints to canonical ones, and describe an algorithm that enables to instill a set of behaviors onto an arbitrary humanoid skeleton.…”

Section: Related Work 21 Motion Retargetingmentioning

confidence: 99%

Skeleton-aware networks for deep motion retargeting

et al. 2020

View full text Add to dashboard Cite

We introduce a novel deep learning framework for data-driven motion retargeting between skeletons, which may have different structure, yet corresponding to homeomorphic graphs. Importantly, our approach learns how to retarget without requiring any explicit pairing between the motions in the training set. We leverage the fact that different homeomorphic skeletons may be reduced to a common primal skeleton by a sequence of edge merging operations, which we refer to as skeletal pooling. Thus, our main technical contribution is the introduction of novel differentiable convolution, pooling, and unpooling operators. These operators are skeleton-aware , meaning that they explicitly account for the skeleton's hierarchical structure and joint adjacency, and together they serve to transform the original motion into a collection of deep temporal features associated with the joints of the primal skeleton. In other words, our operators form the building blocks of a new deep motion processing framework that embeds the motion into a common latent space, shared by a collection of homeomorphic skeletons. Thus, retargeting can be achieved simply by encoding to, and decoding from this latent space. Our experiments show the effectiveness of our framework for motion retargeting, as well as motion processing in general, compared to existing approaches. Our approach is also quantitatively evaluated on a synthetic dataset that contains pairs of motions applied to different skeletons. To the best of our knowledge, our method is the first to perform retargeting between skeletons with differently sampled kinematic chains, without any paired examples.

show abstract

Section: Related Work 21 Motion Retargetingmentioning

confidence: 99%

Skeleton-aware networks for deep motion retargeting

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Motion retargeting is pioneered by [7], which identifies features of the source motions as kinematic constraints and solves the space-time optimization problem. Following it, many optimization-based motion retargeting methods were proposed successively by introducing specific constraints, e.g., dynamics constraints [22], inverse kinematics [14], joint angle constraints [5], Euclidean distance [4], and trajectory constraints [6]. Recently, there has been a surge of interest in studying deep-learning-based motion retargeting.…”

Section: Related Workmentioning

confidence: 99%

Skinned Motion Retargeting with Residual Perception of Motion Semantics & Geometry

Zhang¹,

Weng²,

Kang³

et al. 2023

Preprint

View full text Add to dashboard Cite

A good motion retargeting cannot be reached without reasonable consideration of source-target differences on both the skeleton and shape geometry levels. In this work, we propose a novel Residual RETargeting network (R 2 ET) structure, which relies on two neural modification modules, to adjust the source motions to fit the target skeletons and shapes progressively. In particular, a skeleton-aware module is introduced to preserve the source motion semantics. A shape-aware module is designed to perceive the geometries of target characters to reduce interpenetration and contactmissing. Driven by our explored distance-based losses that explicitly model the motion semantics and geometry, these two modules can learn residual motion modifications on the source motion to generate plausible retargeted motion in a single inference without post-processing. To balance these two modifications, we further present a balancing gate to conduct linear interpolation between them. Extensive experiments on the public dataset Mixamo demonstrate that our R 2 ET achieves the state-of-the-art performance, and provides a good balance between the preservation of motion semantics as well as the attenuation of interpenetration and contact-missing. Code is available at https://github.com/Kebii/R2ET.

show abstract

“…Tak and Ko [TK05] introduced user-specified dynamics constraints with the Kalman filter. Feng et al [FHXS12] defined heuristics in joint chain mapping to retarget between human character models. Other researchers [SOL13,YAH10] extracted keyframe poses that are the candidates of the most similar ones between the source pose and the target pose, so as to re-target from human motion data into non-human motion data.…”

Section: Motion Re-targetingmentioning

confidence: 99%

Simplified Physical Model‐based Balance‐preserving Motion Re‐targeting for Physical Simulation

Hwang,

Ishii

2023

Computer Graphics Forum

View full text Add to dashboard Cite

In this study, we propose a novel motion re‐targeting framework that provides natural motions of target robot character models similar to the given source motions of a different skeletal structure. The natural target motion requires satisfying kinematic constraints to show a similar motion to the source motion although the kinematical structure between the source and the target character models differ from each other. Simultaneously, the target motion should maintain physically plausible features such as keeping the balance of the target character model. To handle the issue, we utilize a simple physics model (an inverted‐pendulum‐on‐a‐cart model) during the motion re‐targeting process. By interpreting the source motion's balancing property via the pendulum model, the target motion inherits the balancing property of the source motion. The inheritance is derived by performing the motion analysis to extract the necessary parameters for re‐targeting the pendulum model's motion pattern and parameter learning to estimate the suitable parameters for the target character model. Based on the simple physics inheritance, the proposed framework provides balance‐preserving target motions, even applicable to the full‐body physics simulation or a real robot control. We validate the framework by experimenting with motion re‐targeting from animal character and human character source models to the quadruped‐ and humanoid‐type target models with Muaythai punching, kicking and walking motions. We also implement comparisons with the existing methods to clarify the enhancement.

show abstract

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

Cited by 13 publications

References 26 publications

Skeleton-aware networks for deep motion retargeting

Skeleton-aware networks for deep motion retargeting

Skinned Motion Retargeting with Residual Perception of Motion Semantics & Geometry

Simplified Physical Model‐based Balance‐preserving Motion Re‐targeting for Physical Simulation

Contact Info

Product

Resources

About