Search For:

Displaying 1-50 out of 66 total
A wave-based anisotropic quadrangulation method
Found in: ACM Transactions on Graphics (TOG)
By Hujun Bao, Jin Huang, Muyang Zhang, Xinguo Liu, Hujun Bao, Jin Huang, Muyang Zhang, Xinguo Liu, Hujun Bao, Jin Huang, Muyang Zhang, Xinguo Liu, Hujun Bao, Jin Huang, Muyang Zhang, Xinguo Liu
Issue Date:July 2010
pp. 1-10
This paper proposes a new method for remeshing a surface into anisotropically sized quads. The basic idea is to construct a special standing wave on the surface to generate the global quadrilateral structure. This wave based quadrangulation method is capab...
     
An efficient GPU-based approach for interactive global illumination
Found in: ACM Transactions on Graphics (TOG)
By Hujun Bao, Kun Zhou, Minghao Pan, Rui Wang, Hujun Bao, Kun Zhou, Minghao Pan, Rui Wang, Hujun Bao, Kun Zhou, Minghao Pan, Rui Wang, Hujun Bao, Kun Zhou, Minghao Pan, Rui Wang
Issue Date:July 2009
pp. 1-2
This paper presents a GPU-based method for interactive global illumination that integrates complex effects such as multi-bounce indirect lighting, glossy reflections, caustics, and arbitrary specular paths. Our method builds upon scattered data sampling an...
     
Structure-Aware Lighting Design for Volume Visualization
Found in: IEEE Transactions on Visualization and Computer Graphics
By Yubo Tao,Hai Lin,Feng Dong,Chao Wang,Gordon Clapworthy,Hujun Bao
Issue Date:December 2012
pp. 2372-2381
Lighting design is a complex, but fundamental, problem in many fields. In volume visualization, direct volume rendering generates an informative image without external lighting, as each voxel itself emits radiance. However, external lighting further improv...
 
An Efficient Direct Volume Rendering Approach for Dichromats
Found in: IEEE Transactions on Visualization and Computer Graphics
By Weifeng Chen,Wei Chen,Hujun Bao
Issue Date:December 2011
pp. 2144-2152
Color vision deficiency (CVD) affects a high percentage of the population worldwide. When seeing a volume visualization result, persons with CVD may be incapable of discriminating the classification information expressed in the image if the color transfer ...
 
Keynote Abstracts
Found in: 2011 Sixth International Conference on Image and Graphics (ICIG 2011)
By Mihaela van der Schaar,Mubarak Shah, Hujun Bao
Issue Date:August 2011
pp. xxv-xxix
These keynote speeches discuss the following: Finding it Now: Stream Mining in Real Time; Patterns of Motion: Discovery and Generalized Representation; and 3D Structure Reconstruction from Videos.
   
Moving Object Extraction with a Hand-held Camera
Found in: Computer Vision, IEEE International Conference on
By Guofeng Zhang, Jiaya Jia, Wei Xiong, Tien-Tsin Wong, Pheng-Ann Heng, Hujun Bao
Issue Date:October 2007
pp. 1-8
This paper presents a new method to detect and accurately extract the moving object from a video sequence taken by a hand-held camera. In order to extract the high quality moving foreground, previous approaches usually assume that the background is static ...
 
Image-Space Texture-Based Output-Coherent Surface Flow Visualization
Found in: IEEE Transactions on Visualization and Computer Graphics
By Jin Huang, Zherong Pan, Guoning Chen, Wei Chen, Hujun Bao
Issue Date:September 2013
pp. 1476-1487
Image-space line integral convolution (LIC) is a popular scheme for visualizing surface vector fields due to its simplicity and high efficiency. To avoid inconsistencies or color blur during the user interactions, existing approaches employ surface paramet...
 
Analytic Double Product Integrals for All-Frequency Relighting
Found in: IEEE Transactions on Visualization and Computer Graphics
By Rui Wang, Minghao Pan, Weifeng Chen, Zhong Ren, Kun Zhou, Wei Hua, Hujun Bao
Issue Date:July 2013
pp. 1133-1142
This paper presents a new technique for real-time relighting of static scenes with all-frequency shadows from complex lighting and highly specular reflections from spatially varying BRDFs. The key idea is to depict the boundaries of visible regions using p...
 
A Divide-and-Conquer Approach to Quad Remeshing
Found in: IEEE Transactions on Visualization and Computer Graphics
By Muyang Zhang, Jin Huang, Xinguo Liu, Hujun Bao
Issue Date:June 2013
pp. 941-952
Many natural and man-made objects consist of simple primitives, similar components, and various symmetry structures. This paper presents a divide-and-conquer quadrangulation approach that exploits such global structural information. Given a model represent...
 
Geodesic Based Semi-supervised Multi-manifold Feature Extraction
Found in: 2012 IEEE 12th International Conference on Data Mining (ICDM)
By Mingyu Fan,Xiaoqin Zhang,Zhouchen Lin,Zhongfei Zhang,Hujun Bao
Issue Date:December 2012
pp. 852-857
Manifold learning is an important feature extraction approach in data mining. This paper presents a new semi-supervised manifold learning algorithm, called Multi-Manifold Discriminative Analysis (Multi-MDA). The proposed method is designed to explore the d...
 
Consistent depth maps recovery from a trinocular video sequence
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Wenzhuo Yang, Guofeng Zhang, Hujun Bao, Jiwon Kim, Ho Young Lee
Issue Date:June 2012
pp. 1466-1473
In this paper, we propose a novel dense depth recovery method for a trinocular video sequence. Specifically, we contribute a novel trinocular stereo matching model, which can effectively utilize the advantages of trinocular stereo images, and incorporate t...
 
Output-coherent image-space LIC for surface flow visualization
Found in: Visualization Symposium, IEEE Pacific
By Jin Huang,Wenjie Pei,Chunfeng Wen,Guoning Chen,Wei Chen,Hujun Bao
Issue Date:March 2012
pp. 137-144
Image-space line integral convolution (LIC) is a popular approach for visualizing surface vector fields due to its simplicity and high efficiency. To avoid inconsistencies or color blur during the user interactions in the image-space approach, some methods...
 
Simultaneous multi-body stereo and segmentation
Found in: Computer Vision, IEEE International Conference on
By Guofeng Zhang,Jiaya Jia,Hujun Bao
Issue Date:November 2011
pp. 826-833
This paper presents a novel multi-body multi-view stereo method to simultaneously recover dense depth maps and perform segmentation with the input of a monocular image sequence. Unlike traditional multi-view stereo approaches that generally handle a single...
 
Non-negative local coordinate factorization for image representation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yan Chen, Hujun Bao, Xiaofei He
Issue Date:June 2011
pp. 569-574
Recently Non-negative Matrix Factorization (NMF) has become increasingly popular for feature extraction in computer vision and pattern recognition. NMF seeks for two non-negative matrices whose product can best approximate the original matrix. The non-nega...
 
Sparse concept coding for visual analysis
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Deng Cai, Hujun Bao, Xiaofei He
Issue Date:June 2011
pp. 2905-2910
We consider the problem of image representation for visual analysis. When representing images as vectors, the feature space is of very high dimensionality, which makes it difficult for applying statistical techniques for visual analysis. To tackle this pro...
 
A Variance Minimization Criterion to Feature Selection Using Laplacian Regularization
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Xiaofei He,Ming Ji,Chiyuan Zhang,Hujun Bao
Issue Date:October 2011
pp. 2013-2025
In many information processing tasks, one is often confronted with very high-dimensional data. Feature selection techniques are designed to find the meaningful feature subset of the original features which can facilitate clustering, classification, and ret...
 
Motion Imitation with a Handheld Camera
Found in: IEEE Transactions on Visualization and Computer Graphics
By Guofeng Zhang,Hanqing Jiang,Jin Huang,Jiaya Jia,Tien-Tsin Wong,Kun Zhou,Hujun Bao
Issue Date:October 2011
pp. 1475-1486
In this paper, we present a novel method to extract motion of a dynamic object from a video that is captured by a handheld camera, and apply it to a 3D character. Unlike the motion capture techniques, neither special sensors/trackers nor a controllable env...
 
Laplacian Regularized Gaussian Mixture Model for Data Clustering
Found in: IEEE Transactions on Knowledge and Data Engineering
By Xiaofei He,Deng Cai,Yuanlong Shao,Hujun Bao,Jiawei Han
Issue Date:September 2011
pp. 1406-1418
Gaussian Mixture Models (GMMs) are among the most statistically mature methods for clustering. Each cluster is represented by a Gaussian distribution. The clustering process thereby turns to estimate the parameters of the Gaussian mixture, usually by the E...
 
Interactive Shape Interpolation through Controllable Dynamic Deformation
Found in: IEEE Transactions on Visualization and Computer Graphics
By Jin Huang, Yiying Tong, Kun Zhou, Hujun Bao, Mathieu Desbrun
Issue Date:July 2011
pp. 983-992
In this paper, we introduce an interactive approach to generate physically based shape interpolation between poses. We extend linear modal analysis to offer an efficient and robust numerical technique to generate physically-plausible dynamics even for very...
 
Robust Bilayer Segmentation and Motion/Depth Estimation with a Handheld Camera
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Guofeng Zhang, Jiaya Jia, Wei Hua, Hujun Bao
Issue Date:March 2011
pp. 603-617
Extracting high-quality dynamic foreground layers from a video sequence is a challenging problem due to the coupling of color, motion, and occlusion. Many approaches assume that the background scene is static or undergoes the planar perspective transformat...
 
Locally Developable Constraint for Document Surface Reconstruction
Found in: Document Analysis and Recognition, International Conference on
By Yuanlong Shao, Xinguo Liu, Xueying Qin, Yi Xu, Hujun Bao
Issue Date:July 2009
pp. 226-230
This article presents a global optimization approach to reconstruct surfaces from a single document image. Instead of assuming globally developable in previous works which restricted the surface to be cylindrical, conical, etc, we use a free form parametri...
 
A unified active and semi-supervised learning framework for image compression
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Xiaofei He, Ming Ji, Hujun Bao
Issue Date:June 2009
pp. 65-72
We consider the problem of lossy image compression from machine learning perspective. Typical image compression algorithms first transform the image from its spatial domain representation to frequency domain representation using some transform technique, s...
 
Refilming with Depth-Inferred Videos
Found in: IEEE Transactions on Visualization and Computer Graphics
By Guofeng Zhang, Zilong Dong, Jiaya Jia, Liang Wan, Tien-Tsin Wong, Hujun Bao
Issue Date:September 2009
pp. 828-840
Compared to still image editing, content-based video editing faces the additional challenges of maintaining the spatiotemporal consistency with respect to geometry. This brings up difficulties of seamlessly modifying video content, for instance, inserting ...
 
Consistent Depth Maps Recovery from a Video Sequence
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Guofeng Zhang, Jiaya Jia, Tien-Tsin Wong, Hujun Bao
Issue Date:June 2009
pp. 974-988
This paper presents a novel method for recovering consistent depth maps from a video sequence. We propose a bundle optimization framework to address the major difficulties in stereo reconstruction, such as dealing with image noise, occlusions, and outliers...
 
Stereoscopic Video Synthesis from a Monocular Video
Found in: IEEE Transactions on Visualization and Computer Graphics
By Guofeng Zhang, Wei Hua, Xueying Qin, Tien-Tsin Wong, Hujun Bao
Issue Date:July 2007
pp. 686-696
<p><b>Abstract</b>—This paper presents an automatic and robust approach to synthesize stereoscopic videos from ordinary monocular videos acquired by commodity video cameras. Instead of recovering the depth map, the proposed method synthes...
 
Robust Metric Reconstruction from Challenging Video Sequences
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Guofeng Zhang, Xueying Qin, Wei Hua, Tien-Tsin Wong, Pheng-Ann Heng, Hujun Bao
Issue Date:June 2007
pp. 1-8
Although camera self-calibration and metric reconstruction have been extensively studied during the past decades, automatic metric reconstruction from long video sequences with varying focal length is still very challenging. Several critical issues in prac...
 
Regular B?zier Curve: Some geometric conditions and a necessary and sufficient condition
Found in: Computer Aided Design and Computer Graphics, International Conference on
By Hongwei Lin, Hujun Bao
Issue Date:December 2005
pp. 52-57
The regularity is an important algebraic property for the parametric curve and surface, which depends on their parameterizations. Therefore, determining the regularity of parametric curves or surfaces is a basic problem in evaluating the quality of their p...
 
Computing variation modes for point set surfaces
Found in: Proceedings Eurographics/IEEE VGTC Symposium Point-Based Graphics
By X. Liu, Hujun Bao, Qunsheng Peng, B. Guo
Issue Date:June 2005
pp. 63-69
Point sets have become a popular shape representation. In this paper, we present a novel approach to computing variation modes for point set surfaces, and represent the point set surface as a linear combination of the variation modes, called a generative r...
 
Importance-driven texture encoding based on samples
Found in: Computer Graphics International Conference
By Ying Tang, Hongxin Zhang, Qing Wang, Hujun Bao
Issue Date:June 2005
pp. 169-176
In this paper, we present an importance-driven texture encoding algorithm based on samples. Our algorithm determines a set of samples from source texture based on combined criteria which include compression ratio, visual attention and parameterization dist...
 
Real-time Voxelization for Complex Polygonal Models
Found in: Computer Graphics and Applications, Pacific Conference on
By Zhao Dong, Wei Chen, Hujun Bao, Hongxin Zhang, Qunsheng Peng
Issue Date:October 2004
pp. 43-50
In this paper we present an efficient voxelization algorithm for complex polygonal models by exploiting newest programmable graphics hardware. We first convert the model into three discrete voxel spaces according to its surface orientation. The resultant v...
 
Generalized NURBS Curves and Surfaces
Found in: Geometric Modeling and Processing
By Qing Wang, Wei Hua, Guiqing Li, Hujun Bao
Issue Date:April 2004
pp. 365
A novel representation, the generalized NURBS(G-NURBS), is proposed for modeling parametric curves and surfaces. G-NURBS provides a unified framework for traditional parametric curve and surface. G-NURBS surface based on arbitrary irregular mesh, can repre...
 
Interpolatory √2-Subdivision Surfaces
Found in: Geometric Modeling and Processing
By Guiqing Li, Weiyin Ma, Hujun Bao
Issue Date:April 2004
pp. 185
This paper presents a new interpolatory subdivision for quadrilateral meshes. The proposed scheme employs a √2 split operator to refine a given control mesh such that the face number of the refined mesh is doubled after each refinement. For regular meshes,...
 
Practical Super-Resolution from Dynamic Video Sequences
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Zhongding Jiang, Tien-Tsin Wong, Hujun Bao
Issue Date:June 2003
pp. 549
This paper introduces a practical approach for super-resolution, the process of reconstructing a high-resolution image from the low-resolution input ones. The emphasis of our work is to super-resolve frames from dynamic video sequences which may contain si...
 
A Morphing with Geometric Continuity between Two Arbitrary Planar Polygons
Found in: Computer Graphics and Applications, Pacific Conference on
By Youdong Liang, Hujun Bao, Weihua Zhou
Issue Date:October 2002
pp. 448
This paper introduces the geometric continuity equations of the closed planar polygons and gives the definition of a morphing with geometric continuity between two arbitrary planar polygons, including simple, non-3 and even degenerated polygons. A simple m...
   
Non-Distorted Texture Mapping Using Variational Interpolation
Found in: Computer Graphics and Applications, Pacific Conference on
By Ying Tang, Hujun Bao, Qunsheng Peng, Florence Y Mong
Issue Date:October 2000
pp. 402
This paper presents a new efficient texture-mapping algorithm for polygonal meshes. Texture coordinates are assigned to the vertices of the mesh using the variational interpolation technique. For each patch to be mapped, the algorithm first samples equidis...
 
Progressive Geometry Compression for Meshes
Found in: Computer Graphics and Applications, Pacific Conference on
By Xinguo Liu, Hujun Bao, Qunsheng Peng, PhengAnn Heng, TienTsin Wong, Hanqiu Sun
Issue Date:October 2000
pp. 408
A novel progressive geometry compression scheme is presented in the paper. In this scheme a mesh is represented as a base mesh followed by some groups of vertex split operations using an improved simplification method, in which each level of the mesh can b...
 
A Distributed Hybrid Rendering Algorithm for Highly Complex Scenes
Found in: Computer Graphics and Applications, Pacific Conference on
By Wenting Zheng, Hujun Bao, Qunsheng Peng, Hanqiu Sun
Issue Date:October 1999
pp. 222
A distributed virtual reality system base on a hybrid rendering scheme is presented in this paper. Unlike the traditional image based rending algorithm, our approach divides the local scene within the frustum of the current viewpoint into two layers, i.e.,...
 
Nonlinear View Interpolation
Found in: Computer Graphics and Applications, Pacific Conference on
By Hujun Bao, Li Chen, Jianguo Ying, Qunsheng Peng
Issue Date:October 1998
pp. 61
A new nonlinear view interpolation algorithm is presented in the paper. Unlike the linear interpolation scheme, our method can exactly simulate the perspective viewing transformation during the walkthrough. To accelerate the view interpolation, the algorit...
 
Boundary aligned smooth 3D cross-frame field
Found in: ACM Transactions on Graphics (TOG)
By Hongyu Wei, Hujun Bao, Jin Huang, Yiying Tong, Hongyu Wei, Hujun Bao, Jin Huang, Yiying Tong
Issue Date:December 2011
pp. 1-15
In this paper, we present a method for constructing a 3D cross-frame field, a 3D extension of the 2D cross-frame field as applied to surfaces in applications such as quadrangulation and texture synthesis. In contrast to the surface cross-frame field (equiv...
     
Out-of-core multigrid solver for streaming meshes
Found in: ACM Transactions on Graphics (TOG)
By Hujun Bao, Kun Zhou, Xiaohan Shi, Hujun Bao, Kun Zhou, Xiaohan Shi
Issue Date:December 2009
pp. 1-2
We present an out-of-core multigrid for solving the Poisson equation defined over gigantic meshes. This enables gradient-domain operations on out-of-core meshes with irregular connectivity. Taking a streaming mesh and boundary constraints as input, our sol...
     
Frame Field Singularity Correctionfor Automatic Hexahedralization
Found in: IEEE Transactions on Visualization and Computer Graphics
By Tengfei Jiang,Jin Huang,Yuanzhen Wang,Yiying Tong,Hujun Bao
Issue Date:August 2014
pp. 1189-1199
We present an automatic hexahedralization tool, based on a systematic treatment that removes some of the singularities that would lead to degenerate volumetric parameterization. Such singularities could be abundant in automatically generated frame fields g...
 
Interactive localized liquid motion editing
Found in: ACM Transactions on Graphics (TOG)
By Hujun Bao, Jin Huang, Yiying Tong, Zherong Pan, Changxi Zheng
Issue Date:November 2013
pp. 1-10
Animation techniques for controlling liquid simulation are challenging: they commonly require carefully setting initial and boundary conditions or performing a costly numerical optimization scheme against user-provided keyframes or animation sequences. Eit...
     
GPU-based out-of-core many-lights rendering
Found in: ACM Transactions on Graphics (TOG)
By Hujun Bao, Kun Zhou, Wei Hua, Yuchi Huo, Rui Wang, Yazhen Yuan
Issue Date:November 2013
pp. 1-10
In this paper, we present a GPU-based out-of-core rendering approach under the many-lights rendering framework. Many-lights rendering is an efficient and scalable rendering framework for a large number of lights. But when the data sizes of lights and geome...
     
Boundary aligned smooth 3D cross-frame field
Found in: Proceedings of the 2011 SIGGRAPH Asia Conference (SA '11)
By Hongyu Wei, Hujun Bao, Jin Huang, Yiying Tong
Issue Date:December 2011
pp. 1-137
In this paper, we present a method for constructing a 3D cross-frame field, a 3D extension of the 2D cross-frame field as applied to surfaces in applications such as quadrangulation and texture synthesis. In contrast to the surface cross-frame field (equiv...
     
Boundary aligned smooth 3D cross-frame field
Found in: Proceedings of the 2011 SIGGRAPH Asia Conference (SA '11)
By Hongyu Wei, Hujun Bao, Jin Huang, Yiying Tong
Issue Date:December 2011
pp. 1-8
In this paper, we present a method for constructing a 3D cross-frame field, a 3D extension of the 2D cross-frame field as applied to surfaces in applications such as quadrangulation and texture synthesis. In contrast to the surface cross-frame field (equiv...
     
A wave-based anisotropic quadrangulation method
Found in: ACM SIGGRAPH 2010 papers (SIGGRAPH '10)
By Hujun Bao, Jin Huang, Muyang Zhang, Xinguo Liu
Issue Date:July 2010
pp. 10-18
This paper proposes a new method for remeshing a surface into anisotropically sized quads. The basic idea is to construct a special standing wave on the surface to generate the global quadrilateral structure. This wave based quadrangulation method is capab...
     
Out-of-core multigrid solver for streaming meshes
Found in: ACM SIGGRAPH Asia 2009 papers (SIGGRAPH Asia '09)
By Hujun Bao, Kun Zhou, Xiaohan Shi
Issue Date:December 2009
pp. 1-6
We present an out-of-core multigrid for solving the Poisson equation defined over gigantic meshes. This enables gradient-domain operations on out-of-core meshes with irregular connectivity. Taking a streaming mesh and boundary constraints as input, our sol...
     
Semi-supervised topic modeling for image annotation
Found in: Proceedings of the seventeen ACM international conference on Multimedia (MM '09)
By Deng Cai, Hujun Bao, Xiaofei He, Yuan Zhou, Yuanlong Shao
Issue Date:October 2009
pp. 521-524
We propose a novel technique for semi-supervised image annotation which introduces a harmonic regularizer based on the graph Laplacian of the data into the probabilistic semantic model for learning latent topics of the images. By using a probabilistic sema...
     
An efficient GPU-based approach for interactive global illumination
Found in: ACM SIGGRAPH 2009 papers (SIGGRAPH '09)
By Hujun Bao, Kun Zhou, Minghao Pan, Rui Wang
Issue Date:August 2009
pp. 3-3
This paper presents a GPU-based method for interactive global illumination that integrates complex effects such as multi-bounce indirect lighting, glossy reflections, caustics, and arbitrary specular paths. Our method builds upon scattered data sampling an...
     
Spectral quadrangulation with orientation and alignment control
Found in: ACM Transactions on Graphics (TOG)
By Hujun Bao, Jin Huang, Jin Ma, Leif Kobbelt, Muyang Zhang, Xinguo Liu
Issue Date:December 2008
pp. 1-49
This paper presents a new quadrangulation algorithm, extending the spectral surface quadrangulation approach where the coarse quadrangular structure is derived from the Morse-Smale complex of an eigenfunction of the Laplacian operator on the input mesh. In...
     
 1  2 Next >>