Splicing Upper‐Body Actions with Locomotion

Heck, Rachel; Kovar, Lucas; Gleicher, Michael

doi:10.1111/j.1467-8659.2006.00965.x

Cited by 44 publications

(38 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To date, researchers have focused on creating splicing methods for specific parts and situations, such as hands [28]. In [29] we presented a method for splicing upper body motions onto lower bodies in the specific case where both examples come from locomotion. The method works by specifically identifying important types of couplings, including posture, coordinated timing, and spatial alignment, and taking specific steps to make sure that each coupling is properly established in the result.…”

Section: Splicing Actionsmentioning

confidence: 99%

More Motion Capture in Games — Can We Make Example-Based Approaches Scale?

Gleicher

2008

Motion in Games

Self Cite

View full text Add to dashboard Cite

Abstract. Synthesis-by-Example (SBE) approaches have been successful at animating characters in both research and practice (games). These approaches assemble motions from pre-recorded examples, usually motion captured or keyframed. To date, the methods have relied on a small set of simple, generic building blocks for assembling the motions. To meet the increasing demands for better character movement and control in games, the approaches will need to evolve. An obvious path to address these challenges, employing increasingly large collections of examples, is enabled by recent research. However, scaling up the number of examples is unlikely to sufficiently scale up the quality of the character animation. Methods that make better use of examples will be required.

show abstract

Section: Splicing Actionsmentioning

confidence: 99%

More Motion Capture in Games — Can We Make Example-Based Approaches Scale?

Gleicher

2008

Motion in Games

Self Cite

View full text Add to dashboard Cite

show abstract

“…Ikemoto et al [16] designed several rules for transplanting limbs. Heck et al [17] studied methods to splice upper body motion and locomotion. Differing from these, we are studying acyclic motions and no clear coordination rules were observed between body parts.…”

Section: Literaturementioning

confidence: 99%

A Perceptual Study of the Relationship between Posture and Gesture for Virtual Characters

Luo

Neff

2012

Motion in Games

View full text Add to dashboard Cite

Abstract. Adding expressive body motions that synchronizes with gestures appropriately is a key element in creating a lively, intelligent virtual character. However, little is known about the relationship between body motions and gestures or how sensitive humans are to the errors generated by desynchronized gesture and body motion. In this paper, we investigated the motion splicing technique used for aligning body motion and studied people's sensitivity to desynchronized body motions through two experiments. The first experiment is designed to see whether audio will affect people's sensitivity to desynchronization errors and explore the role of Posture-Gesture Mergers in the transferability of body motion. A motion distance metric for measuring the distance between stylistically varied body motions is proposed and evaluated in a second experiment. The experiments revealed that audio does not affect the recognition rate, but the presence of posture gesture mergers in the source motion lowers output quality, and people's sensitivity to motion realism is related to an energy distance metric.

show abstract

“…One important and challenging motion processing problem is motion registration, which finds temporal correspondences between structurally similar motion sequences. Motion registration has many important applications; for instance, registered motions have been used for motion interpolation [Bruderlin and Williams 1995;Guo and Roberge 1996;Wiley and Hahn 1997;Rose et al 1998;Park et al 2002;Kovar and Gleicher 2004;Mukai and Kuriyama 2005], motion transfer [Hsu et al 2005;Heck et al 2006] and realtime motion control [Cooper et al 2007]. (right) the red and green curves show the result from dynamic time warping and ground-truth result from manual registeration respectively.…”

Section: Introductionmentioning

confidence: 99%

Flexible registration of human motion data with parameterized motion models

Chen¹,

Min²,

Chai³

2009

Proceedings of the 2009 Symposium on Interactive 3D Graphics and Games

View full text Add to dashboard Cite

Figure 1: Our registration method automatically registers two motions by registering each motion with the parameterized walking model. AbstractThis paper presents an efficient model-based approach for automatic human motion registration, which builds temporal correspondences between structurally similar but distinctive motion examples. The key idea of the model-based registration process is to construct a parameterized motion model from a set of preregistered motion examples. With such a model, we can register an input motion with the parameterized motion model by continuously deforming the model to best match the input motion. We formulate the registration process in a gradient-based nonlinear optimization framework by minimizing an objective function that measures differences between the input motion and deforming motion. We also develop a multi-resolution optimization process to efficiently estimate the model parameters as well as the temporal correspondences between the input motion and deforming motion. We demonstrate the performance of our approach by testing the algorithm on difficult motion sequences and comparing with alternative approaches.

show abstract

Splicing Upper‐Body Actions with Locomotion

Abstract: This paper presents a simple and efficient

Cited by 44 publications

References 30 publications

More Motion Capture in Games — Can We Make Example-Based Approaches Scale?

More Motion Capture in Games — Can We Make Example-Based Approaches Scale?

A Perceptual Study of the Relationship between Posture and Gesture for Virtual Characters

Flexible registration of human motion data with parameterized motion models

Contact Info

Product

Resources

About