Weiwei Xu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Weiwei Xu has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Kun Zhou
State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China
5 shared publications - Huamin Wang
Ohio State University
3 shared publications Kun Zhou
3 shared publications- Yin Yang
University of Utah, Salt Lake City, USA
3 shared publications Baining Guo
2 shared publications- Ran Luo
Electrical and Computer Engineering Department, University of New Mexico, 1104 Albuquerque, New Mexico United States 87106
2 shared publications
Latest Publications
- 15 November 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. PP (10772626) , 1
NNWarp: Neural Network-based Nonlinear Deformation
NNWarp is a highly re-usable and efficient neural network (NN) based nonlinear deformable simulation framework. Unlike other machine learning applications such as image recognition, where different inputs have a uniform and consistent format (e.g. an array of all the pixels in an image), the input for deformable simulation is quite variable, high-dimensional, and parametrization-unfriendly. Consequently, even though the neural network is known for its rich expressivity of nonlinear functions, directly using an NN to reconstruct the force-displacement relation for general deformable simulation is nearly impossible. NNWarp obviates this difficulty by partially restoring the force-displacement relation via warping the nodal displacement simulated using a simplistic constitutive model - the linear elasticity. In other words, NNWarp yields an incremental displacement fix per mesh node based on a simplified (therefore incorrect) simulation result other than synthesizing the unknown displacement directly. We introduce a compact yet effective feature vector including geodesic, potential and digression to sort training pairs of per-node linear and nonlinear displacement. NNWarp is robust under different model shapes and tessellations. With the assistance of deformation substructuring, one NN training is able to handle a wide range of 3D models of various geometries. Thanks to the linear elasticity and its constant system matrix, the underlying simulator only needs to perform one pre-factorized matrix solve at each time step, which allows NNWarp to simulate large models in real time.
- 15 November 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. PP (10772626) , 1
NNWarp: Neural Network-based Nonlinear Deformation
NNWarp is a highly re-usable and efficient neural network (NN) based nonlinear deformable simulation framework. Unlike other machine learning applications such as image recognition, where different inputs have a uniform and consistent format (e.g. an array of all the pixels in an image), the input for deformable simulation is quite variable, high-dimensional, and parametrization-unfriendly. Consequently, even though the neural network is known for its rich expressivity of nonlinear functions, directly using an NN to reconstruct the force-displacement relation for general deformable simulation is nearly impossible. NNWarp obviates this difficulty by partially restoring the force-displacement relation via warping the nodal displacement simulated using a simplistic constitutive model - the linear elasticity. In other words, NNWarp yields an incremental displacement fix per mesh node based on a simplified (therefore incorrect) simulation result other than synthesizing the unknown displacement directly. We introduce a compact yet effective feature vector including geodesic, potential and digression to sort training pairs of per-node linear and nonlinear displacement. NNWarp is robust under different model shapes and tessellations. With the assistance of deformation substructuring, one NN training is able to handle a wide range of 3D models of various geometries. Thanks to the linear elasticity and its constant system matrix, the underlying simulator only needs to perform one pre-factorized matrix solve at each time step, which allows NNWarp to simulate large models in real time.
- Open Access
DeepWarp: DNN-based Nonlinear Deformation
DeepWarp is an efficient and highly re-usable deep neural network (DNN) based nonlinear deformable simulation framework. Unlike other deep learning applications such as image recognition, where different inputs have a uniform and consistent format (e.g. an array of all the pixels in an image), the input for deformable simulation is quite variable, high-dimensional, and parametrization-unfriendly. Consequently, even though DNN is known for its rich expressivity of nonlinear functions, directly using DNN to reconstruct the force-displacement relation for general deformable simulation is nearly impossible. DeepWarp obviates this difficulty by partially restoring the force-displacement relation via warping the nodal displacement simulated using a simplistic constitutive model -- the linear elasticity. In other words, DeepWarp yields an incremental displacement fix based on a simplified (therefore incorrect) simulation result other than returning the unknown displacement directly. We contrive a compact yet effective feature vector including geodesic, potential and digression to sort training pairs of per-node linear and nonlinear displacement. DeepWarp is robust under different model shapes and tessellations. With the assistance of deformation substructuring, one DNN training is able to handle a wide range of 3D models of various geometries including most examples shown in the paper. Thanks to the linear elasticity and its constant system matrix, the underlying simulator only needs to perform one pre-factorized matrix solve at each time step, and DeepWarp is able to simulate large models in real time.
Open AccessDeepWarp: DNN-based Nonlinear Deformation
DeepWarp is an efficient and highly re-usable deep neural network (DNN) based nonlinear deformable simulation framework. Unlike other deep learning applications such as image recognition, where different inputs have a uniform and consistent format (e.g. an array of all the pixels in an image), the input for deformable simulation is quite variable, high-dimensional, and parametrization-unfriendly. Consequently, even though DNN is known for its rich expressivity of nonlinear functions, directly using DNN to reconstruct the force-displacement relation for general deformable simulation is nearly impossible. DeepWarp obviates this difficulty by partially restoring the force-displacement relation via warping the nodal displacement simulated using a simplistic constitutive model -- the linear elasticity. In other words, DeepWarp yields an incremental displacement fix based on a simplified (therefore incorrect) simulation result other than returning the unknown displacement directly. We contrive a compact yet effective feature vector including geodesic, potential and digression to sort training pairs of per-node linear and nonlinear displacement. DeepWarp is robust under different model shapes and tessellations. With the assistance of deformation substructuring, one DNN training is able to handle a wide range of 3D models of various geometries including most examples shown in the paper. Thanks to the linear elasticity and its constant system matrix, the underlying simulator only needs to perform one pre-factorized matrix solve at each time step, and DeepWarp is able to simulate large models in real time.
- Open Access
Efficiently Disassemble-and-Pack for Mechanism
In this paper, we present a disassemble-and-pack approach for a mechanism to seek a box which contains total mechanical parts with high space utilization. Its key feature is that mechanism contains not only geometric shapes but also internal motion structures which can be calculated to adjust geometric shapes of the mechanical parts. Our system consists of two steps: disassemble mechanical object into a group set and pack them within a box efficiently. The first step is to create a hierarchy of possible group set of parts which is generated by disconnecting the selected joints and adjust motion structures of parts in groups. The aim of this step is seeking total minimum volume of each group. The second step is to exploit the hierarchy based on breadth-first-search to obtain a group set. Every group in the set is inserted into specified box from maximum volume to minimum based on our packing strategy. Until an approximated result with satisfied efficiency is accepted, our approach finish exploiting the hierarchy.
Open AccessEfficiently Disassemble-and-Pack for Mechanism
In this paper, we present a disassemble-and-pack approach for a mechanism to seek a box which contains total mechanical parts with high space utilization. Its key feature is that mechanism contains not only geometric shapes but also internal motion structures which can be calculated to adjust geometric shapes of the mechanical parts. Our system consists of two steps: disassemble mechanical object into a group set and pack them within a box efficiently. The first step is to create a hierarchy of possible group set of parts which is generated by disconnecting the selected joints and adjust motion structures of parts in groups. The aim of this step is seeking total minimum volume of each group. The second step is to exploit the hierarchy based on breadth-first-search to obtain a group set. Every group in the set is inserted into specified box from maximum volume to minimum based on our packing strategy. Until an approximated result with satisfied efficiency is accepted, our approach finish exploiting the hierarchy.
- 14 December 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 24 (12) , 3188-3199
Physics-Based Quadratic Deformation Using Elastic Weighting
This paper presents a spatial reduction framework for simulating nonlinear deformable objects interactively. This reduced model is built using a small number of overlapping quadratic domains as we notice that incorporating high-order degrees of freedom (DOFs) is important for the simulation quality. Departing from existing multi-domain methods in graphics, our method interprets deformed shapes as blended quadratic transformations from nearby domains. Doing so avoids expensive safeguards against the domain coupling and improves the numerical robustness under large deformations. We present an algorithm that efficiently computes weight functions for reduced DOFs in a physics-aware manner. Inspired by the well-known multi-weight enveloping technique, our framework also allows subspace tweaking based on a few representative deformation poses. Such elastic weighting mechanism significantly extends the expressivity of the reduced model with light-weight computational efforts. Our simulator is versatile and can be well interfaced with many existing techniques. It also supports local DOF adaption to incorporate novel deformations (i.e. induced by the collision). The proposed algorithm complements state-of-the-art model reduction and domain decomposition methods by seeking for good trade-offs among animation quality, numerical robustness, pre-computation complexity, and simulation efficiency from an alternative perspective.
- 14 December 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 24 (12) , 3188-3199
Physics-Based Quadratic Deformation Using Elastic Weighting
This paper presents a spatial reduction framework for simulating nonlinear deformable objects interactively. This reduced model is built using a small number of overlapping quadratic domains as we notice that incorporating high-order degrees of freedom (DOFs) is important for the simulation quality. Departing from existing multi-domain methods in graphics, our method interprets deformed shapes as blended quadratic transformations from nearby domains. Doing so avoids expensive safeguards against the domain coupling and improves the numerical robustness under large deformations. We present an algorithm that efficiently computes weight functions for reduced DOFs in a physics-aware manner. Inspired by the well-known multi-weight enveloping technique, our framework also allows subspace tweaking based on a few representative deformation poses. Such elastic weighting mechanism significantly extends the expressivity of the reduced model with light-weight computational efforts. Our simulator is versatile and can be well interfaced with many existing techniques. It also supports local DOF adaption to incorporate novel deformations (i.e. induced by the collision). The proposed algorithm complements state-of-the-art model reduction and domain decomposition methods by seeking for good trade-offs among animation quality, numerical robustness, pre-computation complexity, and simulation efficiency from an alternative perspective.
- 22 September 2016
- Published by Wiley in Computer Graphics Forum
- Vol. 36 (6) , 368-380
Stress‐Constrained Thickness Optimization for Shell Object Fabrication
We present an approach to fabricate shell objects with thickness parameters, which are computed to maintain the user‐specified structural stability. Given a boundary surface and user‐specified external forces, we optimize the thickness parameters according to stress constraints to extrude the surface. Our approach mainly consists of two technical components: First, we develop a patch‐based shell simulation technique to efficiently support the static simulation of extruded shell objects using finite element methods. Second, we analytically compute the derivative of stress required in the sensitivity analysis technique to turn the optimization into a sequential linear programming problem. Experimental results demonstrate that our approach can optimize the thickness parameters for arbitrary surfaces in a few minutes and well predict the physical properties, such as the deformation and stress of the fabricated object.
- 22 September 2016
- Published by Wiley in Computer Graphics Forum
- Vol. 36 (6) , 368-380
Stress‐Constrained Thickness Optimization for Shell Object Fabrication
We present an approach to fabricate shell objects with thickness parameters, which are computed to maintain the user‐specified structural stability. Given a boundary surface and user‐specified external forces, we optimize the thickness parameters according to stress constraints to extrude the surface. Our approach mainly consists of two technical components: First, we develop a patch‐based shell simulation technique to efficiently support the static simulation of extruded shell objects using finite element methods. Second, we analytically compute the derivative of stress required in the sensitivity analysis technique to turn the optimization into a sequential linear programming problem. Experimental results demonstrate that our approach can optimize the thickness parameters for arbitrary surfaces in a few minutes and well predict the physical properties, such as the deformation and stress of the fabricated object.
- 6 May 2016
- Published by Springer Nature in Journal of Computer Science and Technology
- Vol. 31 (3) , 463-478
View-Aware Image Object Compositing and Synthesis from Multiple Sources
- 6 May 2016
- Published by Springer Nature in Journal of Computer Science and Technology
- Vol. 31 (3) , 463-478
View-Aware Image Object Compositing and Synthesis from Multiple Sources
- 3 January 2016
- Published by Springer Nature
- p. 325-336
Fast Nearest Neighbor Search in the Hamming Space
- 3 January 2016
- Published by Springer Nature
- p. 325-336
Fast Nearest Neighbor Search in the Hamming Space
- Open Access
- 29 July 2007
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 26 (99) , 91
Direct manipulation of subdivision surfaces on GPUs
- 29 July 2007
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 26 (99) , 91
Open AccessDirect manipulation of subdivision surfaces on GPUs
- Open Access
- 29 July 2007
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 26 (99) , 84
Gradient domain editing of deforming mesh sequences
- 29 July 2007
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 26 (99) , 84
Open AccessGradient domain editing of deforming mesh sequences
- 4 April 2003
- Published by SPIE-Intl Soc Optical Eng
- Vol. 4756, 347-353
EasyBowling: a virtual bowling system for small space
In this paper we describe a virtual bowling game machine called EasyBowling Machine, which is designed and implemented based on techniques such as Virtual Reality, animation, and image processing. To introduce Virtual Reality technique into this virtual bowling game, our system provides a real game mode: players play the game by throwing a real bowling ball, and then the EasyBowling system uses a PC Camera to detect the motion of the real bowling ball. After the motion parameters (ball direction, ball force, et al.) are computed, the movement of the bowling ball and its collision with pins are simulated on a large display screen. The most obvious advantage of such bowling game machine over other existing bowling games is that the system integrates body exercise into game playing. The implementation techniques are discussed in detail, and the prototype system illustrates the feasibility and efficiency of our method.
- 4 April 2003
- Published by SPIE-Intl Soc Optical Eng
- Vol. 4756, 347-353
EasyBowling: a virtual bowling system for small space
In this paper we describe a virtual bowling game machine called EasyBowling Machine, which is designed and implemented based on techniques such as Virtual Reality, animation, and image processing. To introduce Virtual Reality technique into this virtual bowling game, our system provides a real game mode: players play the game by throwing a real bowling ball, and then the EasyBowling system uses a PC Camera to detect the motion of the real bowling ball. After the motion parameters (ball direction, ball force, et al.) are computed, the movement of the bowling ball and its collision with pins are simulated on a large display screen. The most obvious advantage of such bowling game machine over other existing bowling games is that the system integrates body exercise into game playing. The implementation techniques are discussed in detail, and the prototype system illustrates the feasibility and efficiency of our method.