Multi-layer Lattice Model for Real-Time Dynamic Character Deformation

Iwamoto, Naoya; Shum, Hubert P. H.; Yang, Longzhi; Morishima, Shigeo

doi:10.1111/cgf.12749

Cited by 15 publications

(8 citation statements)

References 32 publications

(48 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this summary, we only included research where the organs tissue appearance was addressed. For some tissues, particularly muscles, there is an extensive body of research that addresses their physical behaviour, mostly for computer animation purposes [ISYM15, KPL*16]. Since our focus is on the appearance modelling, these approaches were not included.…”

Section: Human Tissues and Their Modelingmentioning

confidence: 99%

Appearance Modelling of Living Human Tissues

Nunes

Maciel

Meyer³

et al. 2019

Computer Graphics Forum

View full text Add to dashboard Cite

The visual fidelity of realistic renderings in Computer Graphics depends fundamentally upon how we model the appearance of objects resulting from the interaction between light and matter reaching the eye. In this paper, we survey the research addressing appearance modelling of living human tissue. Among the many classes of natural materials already researched in Computer Graphics, living human tissues such as blood and skin have recently seen an increase in attention from graphics research. There is already an incipient but substantial body of literature on this topic, but we also lack a structured review as presented here. We introduce a classification for the approaches using the four types of human tissues as classifiers. We show a growing trend of solutions that use first principles from Physics and Biology as fundamental knowledge upon which the models are built. The organic quality of visual results provided by these Biophysical approaches is mainly determined by the optical properties of biophysical components interacting with light. Beyond just picture making, these models can be used in predictive simulations, with the potential for impact in many other areas.

show abstract

Section: Human Tissues and Their Modelingmentioning

confidence: 99%

Appearance Modelling of Living Human Tissues

Nunes

Maciel

Meyer³

et al. 2019

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…Lee et al [1995] used a mass spring lattice with three layers for facial animation. Recently, multi-layer systems have been proposed to represent the physical properties of each anatomic layer, such as muscle, fat, and skin [Deul and Bender 2013;Iwamoto et al 2015]. The purpose of these multi-layer approaches is to enhance the simulation quality by modeling the human anatomy at a higher resolution whereas our work has a largely opposite goal to simplify the simulation by using the predictive power of statistical methods.…”

Section: Related Workmentioning

confidence: 99%

Data-driven physics for human soft tissue animation

Kim

Pons-Moll²,

Pujades³

et al. 2017

ACM Trans. Graph.

View full text Add to dashboard Cite

Data driven models of human poses and soft-tissue deformations can produce very realistic results, but they only model the visible surface of the human body and cannot create skin deformation due to interactions with the environment. Physical simulations can generalize to external forces, but their parameters are difficult to control. In this paper, we present a layered volumetric human body model learned from data. Our model is composed of a data-driven inner layer and a physics-based external layer. The inner layer is driven with a volumetric statistical body model (VSMPL). The soft tissue layer consists of a tetrahedral mesh that is driven using the finite element method (FEM). Model parameters, namely the segmentation of the body into layers and the soft tissue elasticity, are learned directly from 4D registrations of humans exhibiting soft tissue deformations. The learned two layer model is a realistic full-body avatar that generalizes to novel motions and external forces. Experiments show that the resulting avatars produce realistic results on held out sequences and react to external forces. Moreover, the model supports the retargeting of physical properties from one avatar when they share the same topology.

show abstract

“…To solve the problems, we proposed to synthesize training data using high-quality human models with captured 3D motion data. We employ primary deformation [26] to drive the movement of the models, and motion retargeting [27] to adjust the movement based on the body sizes of the models. We further propose a new 3D feature set called the 3D dense trajectories including 3D trajectories, 3DHOF and 3DMBH.…”

Section: Introductionmentioning

confidence: 99%

“…This paper is based on our previous work presented in [28], but it substantially extends the work in four aspects, which are: (1) We replace the cylinder-based 3D model with several more realistic 3D human models. The motion is retargeted according to the bone dimensions [27] and skinned to the realistic models [26]. (2) We propose the 3D dense trajectories including 3D trajectories, 3DHOF and 3DMBH to better describe the motion in 3D videos.…”

Section: Introductionmentioning

confidence: 99%

Action Recognition From Arbitrary Views Using Transferable Dictionary Learning

Zhang

Shum

Han

et al. 2018

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

Human action recognition is crucial to many practical applications, ranging from human-computer interaction to video surveillance. Most approaches either recognize the human action from a fixed view or require the knowledge of view angle, which is usually not available in practical applications. In this paper, we propose a novel end-to-end framework to jointly learn a view-invariance transfer dictionary and a view-invariant classifier. The result of the process is a dictionary that can project real-world 2D video into a view-invariant sparse representation, as well as a classifier to recognize actions with an arbitrary view. The main feature of our algorithm is the use of synthetic data to extract view-invariance between 3D and 2D videos during the pre-training phase. This guarantees the availability of training data, and removes the hassle of obtaining real-world videos in specific viewing angles. Additionally, for better describing the actions in 3D videos, we introduce a new feature set called the 3D dense trajectories to effectively encode extracted trajectory information on 3D videos. Experimental results on the IXMAS, N-UCLA, i3DPost and UWA3DII datasets show improvements over existing algorithms.

show abstract

Multi-layer Lattice Model for Real-Time Dynamic Character Deformation

Abstract: Abstract

Cited by 15 publications

References 32 publications

Appearance Modelling of Living Human Tissues

Appearance Modelling of Living Human Tissues

Data-driven physics for human soft tissue animation

Action Recognition From Arbitrary Views Using Transferable Dictionary Learning

Contact Info

Product

Resources

About