Predicting Loose-Fitting Garment Deformations Using Bone-Driven Motion Networks

05/03/2022
by   Xiaoyu Pan, et al.
10

We present a learning algorithm that uses bone-driven motion networks to predict the deformation of loose-fitting garment meshes at interactive rates. Given a garment, we generate a simulation database and extract virtual bones from simulated mesh sequences using skin decomposition. At runtime, we separately compute low- and high-frequency deformations in a sequential manner. The low-frequency deformations are predicted by transferring body motions to virtual bones' motions, and the high-frequency deformations are estimated leveraging the global information of virtual bones' motions and local information extracted from low-frequency meshes. In addition, our method can estimate garment deformations caused by variations of the simulation parameters (e.g., fabric's bending stiffness) using an RBF kernel ensembling trained networks for different sets of simulation parameters. Through extensive comparisons, we show that our method outperforms state-of-the-art methods in terms of prediction accuracy of mesh deformations by about 20 in Hausdorff distance and STED. The code and data are available at https://github.com/non-void/VirtualBones.

READ FULL TEXT

page 1

page 4

page 7

research
03/21/2023

3D Human Mesh Estimation from Virtual Markers

Inspired by the success of volumetric 3D pose estimation, some recent hu...
research
10/20/2021

AniFormer: Data-driven 3D Animation with Transformer

We present a novel task, i.e., animating a target 3D object through the ...
research
12/10/2019

Rates of convergence to the local time of Oscillating and Skew Brownian Motions

In this paper a class of statistics based on high frequency observations...
research
09/09/2009

Motion Segmentation by SCC on the Hopkins 155 Database

We apply the Spectral Curvature Clustering (SCC) algorithm to a benchmar...
research
03/10/2020

The Virtual Tailor: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style

In this paper, we present TailorNet, a neural model which predicts cloth...
research
10/20/2021

Dynamic Multi-Person Mesh Recovery From Uncalibrated Multi-View Cameras

Dynamic multi-person mesh recovery has been a hot topic in 3D vision rec...
research
03/10/2020

TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style

In this paper, we present TailorNet, a neural model which predicts cloth...

Please sign up or login with your details

Forgot password? Click here to reset