Variational Auto-Encoder for 3D Garment Deformation Prediction

Shi, Min; Feng, Wei; Wei, Yukun; Mao, Tianlu; Zhu, Daiyin; Wang, Zhaoqi

doi:10.3724/sp.j.1089.2022.19156

Cited by 2 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The resulting set of instances is divided into training, selection, and testing subsets accounting for 60%, 20%, and 20% of the original instances, respectively. To provide a suitable range for all inputs, the dataset is scaled using the min-max scaling as shown in Equation (22), where x denotes the data before scaling, X denotes the data after scaling, and min and max denote the minimum and maximum values in the dataset, respectively. The scaled dataset ranges from −1 to 1.…”

Section: Neural Network Fusion-based Collision Detection Algorithmmentioning

confidence: 99%

“…Holden et al [17] combined subspace methods for simulation with machine learning, which when coupled, could enable very effective physical simulations of the supported subspaces. The use of machine learning combined with cloth simulations allows cloths to have greater details [18,19] and enriches the pleated meshes of low-resolution cloths [20]. Jin et al [2] used deep neural networks (DNN) to accelerate the detection speed for a bounding box and improve the efficiency of self-collision detection.…”

Section: Introductionmentioning

confidence: 99%

“…Oh et al [21] proposed a cloth simulation method by combining DNNs with traditional physical methods. Shi et al [22] used machine learning to study the relationship between human movement and costume deformation in costume animation, so as to make the cloth more accurate. Jiang et al [23] proposed a method to simulate cloth drape by using different cloth.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep Neural Network-Based Cloth Collision Detection Algorithm

Jin,

Shi,

Yang

et al. 2024

Scientific Programming

View full text Add to dashboard Cite

The quality of collision detection algorithm directly affects the performance of the whole simulation system. To address the low efficiency and low accuracy in detecting the collisions of flexible cloths in virtual environments, this paper proposes an oriented bounding box (OBB) algorithm with a simplified model, tree structure for a root-node double bounding box, and continuous collision detection algorithm incorporating an OpenNN-based neural network optimization. First, for objects interacting with the cloths with more complex modeling, the model is simplified with a surface simplification algorithm based on the quadric error metrics, and the simplified model is used to construct an OBB. Second, a bounding box technique commonly used for collision detection is improved, and a root-node double bounding box algorithm is proposed to reduce the construction time for the bounding box. Finally, neural networks are used to optimize the continuous collision detection algorithm, as neural networks can efficiently process large amounts of data and remove disjoint collision pairs. An experiment shows that the construction of an OBB using the simplified model is almost identical to that of the original model, but the taken to construct the OBB is reduced by a factor of approximately 2.7. For the same cloth, it takes 5.51%–11.32% less time to run the root-node double bounding box algorithm than the traditional-hybrid bounding box algorithm. With an average removal rate nearly identical to that of the traditional filtering method, the elapsed time is reduced by 7%–11% by using the continuous collision detection algorithm based on an OpenNN neural network optimization. The simulation results are realistic and in line with the requirements for real-time cloth simulations.

show abstract

Section: Neural Network Fusion-based Collision Detection Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Neural Network-Based Cloth Collision Detection Algorithm

Jin,

Shi,

Yang

et al. 2024

Scientific Programming

View full text Add to dashboard Cite

show abstract

“…Deng et al [4], based on the research method of Guan et al, extracted 11 joint nodes of human body which affected the garment deformation, extracted the characteristics of human body movement and garment deformation by using BP neural network, and preliminarily found the relationship between human body movement and garment deformation. Shi et al [5] further defined the character of each joint and used four different machine learning models to learn the relationship between human motion and garment deformation from examples, so as to obtain the deformation degree of each area of garment. Santesteban et al [6] trained an MLP and an RNN to simulate a garment model by decomposing the garment deformation into static and dynamic folds.…”

Section: Related Workmentioning

confidence: 99%

Research on Multi-Precision Fabric Modeling Method Based on Machine Learning

Jin

Chen

et al. 2022

Scientific Programming

View full text Add to dashboard Cite

In order to solve the shortcomings of complex calculation and time consumption of fabric physical simulation methods, many single-precision fabric simulation technologies based on machine learning methods have emerged and the amount of calculation is increased for regions with small changes. Aiming at this problem, this paper proposes two multi-precision fabric modeling method based on machine learning. Firstly, the fabric mesh is simulated by the physical method, the initial position of the vertex is calculated, and the deformation of each region of the fabric is measured by Rayleigh quotient curvature, and the multi-precision fabric mesh is constructed. Secondly, the multi-precision fabric graph structure and geometry image are extracted from the multiprecision fabric mesh. Finally, the subgraph convolutional neural network and super-resolution network are trained to model the multi-precision fabric, and we compared the two different multi-precision fabric machine learning modeling methods. Through the experimental verification, in the garment modeling, the garment modeled by the subgraph convolutional neural network is no longer only dependent on the change of human joints, resulting in a more realistic effect. At the same time, the efficiency of the subgraph convolutional neural network is 25.3% higher than that of the single-precision garment modeling based on the machine learning method. In the cloth simulation, speed of the super-resolution network is nearly 16 times faster than that of the physical simulation, which supplements the imperfection of insufficient flexibility of the subgraph convolutional neural network modeling.

show abstract

Variational Auto-Encoder for 3D Garment Deformation Prediction

Cited by 2 publications

References 12 publications

Deep Neural Network-Based Cloth Collision Detection Algorithm

Deep Neural Network-Based Cloth Collision Detection Algorithm

Research on Multi-Precision Fabric Modeling Method Based on Machine Learning

Contact Info

Product

Resources

About