Projects and Publications of Chen's Group

colorline

This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All person copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

     

Publications in Outdoor Laser Scanning

colorline

Capturing and animating real-world scenes have been a major interest and challenge of computer graphics and vision. Its application includes site preservation, urban planning, digital design, tele-conferencing, gaming, and entertainment. We capitalize the latest advancements in laser scanning technology to acquire 3D images of outdoor objects and takes two approaches toward handling point clouds of unprecedentedly large size and yet inherently incomplete and noisy geometry sampling: directly conducting artistic abstraction and depiction of point clouds and constructing full geometry using knowledge about the objects.

Towards Micro-video Understanding by Joint Sequential-Sparse Modeling
newTowards Micro-video Understanding by Joint Sequential-Sparse Modeling

Meng Liu, Liqiang Nie, Meng Wang, Baoquan Chen,
ACM International Conference on Multimedia(ACM MM 2017) [pdf]
A Generic Deep Architecture for Single Image Reflection Removal and Image Smoothing
newA Generic Deep Architecture for Single Image Reflection Removal and Image Smoothing

Qingnan Fan, Jiaolong Yang, Gang Hua, Baoquan Chen, David Wipf,
IEEE International Conference on Computer Vision (ICCV 2017) [pdf]
Emotion control of unstructured dance movements
newEmotion control of unstructured dance movements

Andreas Aristidou, Qiong Zeng, Efstathios Stavrakis, KangKang Yin, Daniel Cohen-Or, Yiorgos Chrysanthou, Baoquan Chen
ACM SIGGRAPH / Eurographics Symposium on Computer Animation (SCA) 2017 [pdf]
Revisiting Stress Majorization as a Unified Framework for Interactive Constrained Graph Visualization
newRevisiting Stress Majorization as a Unified Framework for Interactive Constrained Graph Visualization

Yunhai Wang, Yanyan Wang, Yinqi Sun, Lifeng Zhu, Kecheng Lu, Chi-Wing Fu, Michael Sedlmair, Oliver Deussen, Baoquan Chen
IEEE TVCG (Proc. InfoVis 2017), 2018 [pdf]
EdWordle: Consistency-preserving Word Cloud Editing
newEdWordle: Consistency-preserving Word Cloud Editing

Yunhai Wang, Xiaowei Chu, Chen Bao, Lifeng Zhu, Oliver Deussen, Baoquan Chen, Michael Sedlmair
IEEE TVCG (Proc. InfoVis 2017), 2018 [pdf]
A Perception-Driven Approach to Supervised Dimensionality Reduction for Visualization
newA Perception-Driven Approach to Supervised Dimensionality Reduction for Visualization

Yunhai Wang, Kang Feng, Xiaowei Chu, Jiang Zhang, Chi-Wing Fu, Michael Sedlmair, Xiaohui Yu, Baoquan Chen,
IEEE TVCG 2017 [pdf]
Line Graph or Scatter Plot? Automatic Selection of Methods for Visualizing Trends in Time Series
newLine Graph or Scatter Plot? Automatic Selection of Methods for Visualizing Trends in Time Series

Yunhai Wang, Fubo Han, Lifeng Zhu, Oliver Deussen, Baoquan Chen
IEEE Transactions on Visualization and Computer Graphics (TVCG), 2017 [pdf]
Tree Branch Level of Detail Models for Forest Navigation
newTree Branch Level of Detail Models for Forest Navigation

Xiaopeng Zhang, Guanbo Bao, Weiliang Meng, Marc Jaeger, Hongjun Li, Oliver Deussen, Baoquan Chen
Computer Graphics Forum, 2017 [pdf]
3D Attention-Driven Depth Acquisition for Object Identification
3D Attention-Driven Depth Acquisition for Object Identification

Kai Xu, Yifei Shi, Lintao Zheng, Junyu Zhang, Min Liu, Hui Huang, Hao Su, Daniel Cohen-Or, Baoquan Chen
Conditionly accepted to ACM SIGGRAPH Asia 2016 [pdf]
ShapeLearner: Towards Shape-Based Visual Knowledge Harvesting
ShapeLearner: Towards Shape-Based Visual Knowledge Harvesting

Huayong Xu*, Yafang Wang*, Kang Feng, Gerard de Melo, Wei Xu, Andrei Sharf, Baoquan Chen
The European Conference on Artificial Intelligence (ECAI) 2016 *jointly first author [pdf]
A Holistic Approach for Data-Driven Object Cutout
A Holistic Approach for Data-Driven Object Cutout

Huayong Xu, Yangyan Li, Wenzheng Chen, Dani Lischinski, Daniel Cohen-Or, Baoquan Chen
The 13th Asian Conference on Computer Vision (ACCV 16) [pdf]
Synthesizing Training Images for Boosting Human 3D Pose Estimation
Synthesizing Training Images for Boosting Human 3D Pose Estimation

Wenzheng Chen, Huan Wang, Yangyan Li, Hao Su, Changhe Tu, Dani Lischinski, Daniel Cohen-Or, Baoquan Chen
3D Vision 2016 [pdf]
Mobility Fitting using 4D RANSAC
Mobility Fitting using 4D RANSAC

Hao Li*, Guowei Wan*, Honghua Li, Andrei Sharf, Kai Xu, Baoquan Chen
Computer Graphics Forum (SGP 2016) *jointly first author [pdf]
Classification of Gait Anomalies from Kinect
Classification of Gait Anomalies from Kinect

Qiannan Li, Yafang Wang, Andrei Sharf, Ya Cao, Changhe Tu, Baoquan Chen, Shengyuan Yu
Visual Computer 2016 [pdf]
Connected Fermat Spirals for Layered Fabrication
Connected Fermat Spirals for Layered Fabrication

Haisen Zhao, Fanglin Gu, Qixing Huang, J. A. Garcia Galicia, Yong Chen, Changhe Tu, Bedrich Benes, Hao Zhang, Daniel Cohen-Or, Baoquan Chen
Conditionly accepted to ACM SIGGRAPH 2016 [pdf]
Printed Perforated Lampshades for Continuous Projective Images
Printed Perforated Lampshades for Continuous Projective Images

Haisen Zhao, Lin Lu, Yuan Wei, Dani Lischinski, Andrei Sharf, Daniel Cohen-Or, Baoquan Chen
ACM Transactions on Graphics 2016 [pdf]
Mathematical Foundations of Arc Length-Based Aspect Ratio Selection
Mathematical Foundations of Arc Length-Based Aspect Ratio Selection

Fubo Han, Yunhai Wang, Jian Zhang, Oliver Deussen, Baoquan Chen
IEEE PacificVis 2016 [pdf]
Mathematical Foundations of Arc Length-Based Aspect Ratio Selection
ShapeExplorer: Querying and Exploring Shapes using Visual Knowledge

Tong Ge, Yafang Wang, Gerard de Melo, Zengguang Hao, Andrei Sharf, Baoquan Chen
EDBT 2016 [pdf]
Visualizing and Curating Knowledge Graphs over Time and Space
Visualizing and Curating Knowledge Graphs over Time and Space

Tong Ge, Yafang Wang, Gerard de Melo, Haofeng Li, Baoquan Chen
ACL 2016 [pdf]
Tree Modeling with Real Tree-Parts Examples
Tree Modeling with Real Tree-Parts Examples

Ke Xie, Feilong Yan, Andrei Sharf, Oliver Deussen, Hui Huang, Baoquan Chen
IEEE Transactions on Visualization and Computer Graphics 2015 [pdf]
Dapper: Decompose-and-Pack for 3D Printing
Dapper: Decompose-and-Pack for 3D Printing

Xuelin Chen, Hao Zhang, Jinjie Lin, Ruizhen Hu, Lin Lu, Qixing Huang, Bedrich Benes, Daniel Cohen-Or, Baoquan Chen
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2015) [pdf]
JumpCut: Non-Successive Mask Transfer and Interpolation for Video Cutout
JumpCut: Non-Successive Mask Transfer and Interpolation for Video Cutout

Qingnan Fan, Fan Zhong, Dani Lischinski, Daniel Cohen-Or, Baoquan Chen
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2015) [pdf]
Autoscanning for Coupled Scene Reconstruction and Proactive Object Analysis
Autoscanning for Coupled Scene Reconstruction and Proactive Object Analysis

Kai Xu, Hui Huang, Yifei Shi, Hao Li, Pinxin Long, Jianong Caichen, Wei Sun, Baoquan Chen
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2015) [pdf]
Global optimal searching for textureless 3D object tracking
Global optimal searching for textureless 3D object tracking

Guofeng Wang, Bin Wang, Fan Zhong, Xueying Qin, Baoquan Chen
The Visual Computer (Proceeding of CGI 2015) [pdf]
Mobility-Trees for Indoor Scenes Manipulation
Mobility-Trees for Indoor Scenes Manipulation

Andrei Sharf, Hui Huang, Cheng Liang, Jiapei Zhang, Baoquan Chen Minglun Gong,
Computer Graphics Forum (Proceeding of Eurographics 2015) [pdf]
Hallucinating Stereoscopy from a Single Image
Hallucinating Stereoscopy from a Single Image

Qiong Zeng, Wenzheng Chen, Huan Wang, Changhe Tu, Daniel Cohen-Or, Dani Lischinski, Baoquan Chen
Computer Graphics Forum (Proceeding of Eurographics 2015) [pdf]
Skeleton-Intrinsic Symmetrization of Shapes
Skeleton-Intrinsic Symmetrization of Shapes

Qian Zheng, Zhuming Hao, Hui Huang, Kai Xu, Hao Zhang, Daniel Cohen-Or, Baoquan Chen
Computer Graphics Forum (Proceeding of Eurographics 2015) [pdf]
2D-3D Lifting for Shape Reconstruction
2D-3D Lifting for Shape Reconstruction

Liangliang Nan, Andrei Sharf, Baoquan Chen
Computer Graphics Forum (Proceedings of Pacific Graphics 2014) [pdf]
Slippage-free Background Replacement for Hand-held Video
Slippage-free Background Replacement for Hand-held Video

Fan Zhong, Song Yang, Xueying Qin, Dani Lischinski, Daniel Cohen-Or, Baoquan Chen
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2014) [pdf]
Quality-driven Poisson-guided Autoscanning
Quality-driven Poisson-guided Autoscanning

Shihao Wu, Wei Sun, Pinxin Long, Hui Huang, Daniel Cohen-Or, Minglun Gong, Oliver Deussen, Baoquan Chen
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2014) [pdf]
Morfit: Interactive Surface Reconstruction from Incomplete Point Clouds with Curve-Driven Topology and Geometry Control
Morfit: Interactive Surface Reconstruction from Incomplete Point Clouds with Curve-Driven Topology and Geometry Control

Kangxue Yin, Hui Huang, Hao Zhang, Minglun Gong, Daniel Cohen-Or, Baoquan Chen
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2014) [pdf]
Proactive 3D Scanning of Inaccessible Parts
Proactive 3D Scanning of Inaccessible Parts

Feilong Yan, Andrei Sharf, Wenzhen Lin, Hui Huang, Baoquan Chen
ACM Transactions on Graphics (Proceedings of SIGGRAPH 2014) [pdf]
Build-to-Last: Strength to Weight 3D Printed Objects
Build-to-Last: Strength to Weight 3D Printed Objects

Lin Lu, Andrei Sharf, Haisen Zhao, Yuan Wei, Qingnan Fan, Xuelin Chen, Yann Savoye, Changhe Tu, Daniel Cohen-Or, Baoquan Chen
ACM Transactions on Graphics (Proceedings of SIGGRAPH 2014) [pdf]
Inverse Procedural Modeling of Trees
Inverse Procedural Modeling of Trees

Ondrej Stava, Sören Pirk, Julian Kratt, Baoquan Chen Radomír Měch, Oliver Deussen, Bedrich Benes
Computer Graphics Forum, 2014 [pdf]
Flower Reconstruction from a Single Photo
Flower Reconstruction from a Single Photo

Feilong Yan, Minglun Gong, Daniel Cohen-Or, Oliver Deussen, Baoquan Chen
Computer Graphics Forum (Proceeding of Eurographics 2014) [pdf]

"Mind the Gap": Tele-Registration for Structure-Driven Image Completion

Hui Huang, Kangxue Yin, Minglun Gong, Dani Lischinski, Daniel Cohen-Or, Uri Ascher, Baoquan Chen
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2013) [pdf]
Unsupervised co-segmentation of 3D shapes via affinity aggregation spectral clustering
Unsupervised co-segmentation of 3D shapes via affinity aggregation spectral clustering

Zizhao Wu, Yunhai Wang, Ruyang Shou, Baoquan Chen, Xinguo Liu
Computer & Graphics 2013 [pdf]
Projective Analysis for 3D Shape Segmentation
Projective Analysis for 3D Shape Segmentation

Yunhai Wang, Minglun Gong, Tianhua Wang, Daniel Cohen-Or, Hao Zhang, Baoquan Chen
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2013) [pdf]
Sketch-to-Design: Context-based Part Assembly
Analyzing Growing Plants from 4D Point Cloud Data

Yangyan Li, Xiaochen Fan, Niloy J. Mitra, Daniel Chamovitz, Daniel Cohen-Or, Baoquan Chen
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2013) [pdf]
L1-Medial Skeleton of Point Cloud
L1-Medial Skeleton of Point Cloud

Hui Huang, Shihao Wu, Daniel Cohen-Or, Minglun Gong, Hao Zhang, Guiqing Li, Baoquan Chen
ACM Transactions on Graphics (Proceedings of SIGGRAPH 2013) [pdf]
Layered Analysis of Irregular Facades via Symmetry Maximization
Layered Analysis of Irregular Facades via Symmetry Maximization

Hao Zhang, Kai Xu, Wei Jiang, Daniel Cohen-Or, Baoquan Chen
ACM Transactions on Graphics (Proceedings of SIGGRAPH 2013) [pdf]
Sketch-to-Design: Context-based Part Assembly
Sketch-to-Design: Context-based Part Assembly

Xiaohua Xie, Kai Xu, Niloy J. Mitra, Daniel Cohen-Or, Wenyong Gong, Qi Su, Baoquan Chen
Computer Graphics Forum 2013 [pdf]
Multi-Scale Partial Intrinsic Symmetry Detection
Multi-Scale Partial Intrinsic Symmetry Detection

Kai Xu, Hao Zhang, Wei Jiang, Ramsay Dyer, Zhiquan Cheng, Ligang Liu, Baoquan Chen
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2012) [pdf]
Active Co-Analysis of a Set of Shapes
Active Co-Analysis of a Set of Shapes

Yunhai Wang, Shmulik Asafi, Oliver van Kaick, Hao Zhang, Daniel Cohen-Or, Baoquan Chen
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2012) [pdf]
Fit and Diverse: Set Evolution for Inspiring 3D Shape Galleries
Fit and Diverse: Set Evolution for Inspiring 3D Shape Galleries

Kai Xu, Hao Zhang, Daniel Cohen-Or, Baoquan Chen
ACM Transactions on Graphics (Proceedings of SIGGRAPH 2012) [pdf]
Structure-Preserving Retargeting of Irregular 3D Architecture
Structure-Preserving Retargeting of Irregular 3D Architecture

Jinjie Lin, Daniel Cohen-Or, Hao Zhang, Cheng Liang, Andrei Sharf, Oliver Deussen, Baoquan Chen
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2011) [pdf]
Conjoining Gestalt Rules for Abstraction of Architectural Drawings
Conjoining Gestalt Rules for Abstraction of Architectural Drawings

Liangliang Nan, Andrei Sharf, Ke Xie, Tien-Tsin Wong, Oliver Deussen, Daniel Cohen-Or, Baoquan Chen
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2011) [pdf]
Sorting unorganized photo sets for urban reconstruction
Sorting unorganized photo sets for urban reconstruction

Guowei Wan, Noah Snavely, Daniel Cohen-Or, Qian Zheng, Baoquan Chen, Sikun Li
Graphical Models 2012 [pdf]
2D-3D Fusion for Layer Decomposition of Urban Facades
2D-3D Fusion for Layer Decomposition of Urban Facades

Yangyan Li, Qian Zheng, Andrei Sharf, Daniel Cohen-Or, Baoquan Chen, Niloy J. Mitra
IEEE International Conference on Computer Vision(ICCV 2011) [pdf]
Texture Lobe for Tree Modeling
Texture-Lobes for Tree Modeling

Yotam Livny, Soeren Pirk, Feilong Yan, Zhanglin Cheng, Oliver Deussen, Daniel Cohen-Or, Baoquan Chen
ACM Transactions on Graphics (Proceedings of SIGGRAPH 2011) [pdf]
Automatic Reconstruction of Tree Skeletal Structures from Point Clouds
Automatic Reconstruction of Tree Skeletal Structures from Point Clouds

Yotam Livny, Feilong Yan, Matt Olson, Baoquan Chen, Hao Zhang, Jihad El-Sana
ACM Transactions on Graphics (Proceedings of SIGGRAPH ASIA 2010) [pdf]
SmartBoxes for Interactive Urban Reconstruction SmartBoxes for Interactive Urban Reconstruction

Liangliang Nan, Andrei Sharf, HaoZhang, Daniel Cohen-Or, Baoquan Chen
ACM Transactions on Graphics (Proceedings of SIGGRAPH 2010) [pdf]
Non-local Scan Consolidation for 3D Urban Scene
Non-local Scan Consolidation for 3D Urban Scene

Qian Zheng, Andrei Sharf, Guowei Wan, Yangyan Li, Niloy J. Mitra, Baoquan Chen, Daniel Cohen-Or,
ACM Transactions on Graphics (Proceedings of SIGGRAPH 2010) [pdf]
Consensus Skeleton for Non-Rigid Space-Time Registration Consensus Skeleton for Non-Rigid Space-Time Registration

Qian Zheng, Andrei Sharf, Andrea Tagliasacchi, Baoquan Chen, Hao Zhang, Alla Sheffer, Daniel Cohen-Or
Computer Graphics Forum (Proceeding of Eurographics 2010) [pdf]
Efficient and Dynamic Simplification of Line Drawings
Efficient and Dynamic Simplification of Line Drawings

Amit Shesh, Baoquan Chen,
Computer Graphics Forum (Proceedings of Eurographics 2008) [pdf]
Mathematical Foundations of Arc Length-Based Aspect Ratio Selection
Visual Clustering in Parallel Coordinates

Hong Zhou, Xiaoru Yuan, Huamin Qu, Weiwei Cui, Baoquan Chen
Computer Graphics Forum (Proceedings of Eurographics 2008) [pdf]
Mathematical Foundations of Arc Length-Based Aspect Ratio Selection
Peek-in-the-Pic: Flying Through Architectural Scenes From a Single Image

Amit Shesh, Baoquan Chen
Computer Graphics Forum (Proceedings of Eurographics 2008) [pdf]
Mathematical Foundations of Arc Length-Based Aspect Ratio Selection
Energy-Based Hierarchical Edge Clustering of Graphs

Hong Zhou, Xiaoru Yuan, Weiwei Cui, Huamin Qu, Baoquan Chen
PacificVis 2008 [pdf]
Architectural Modeling from Sparsely Scanned Range Data Architectural Modeling from Sparsely Scanned Range Data

[pdf (1MB)] Jie Chen and Baoquan Chen. International Journal of Computer Vision, 2007. [pdf]
Knowledge and heuristic-based modeling of laser-scanned trees Knowledge and heuristic-based modeling of laser-scanned trees

[pdf(4MB)] Hui Xu, Nathan Gossett and Baoquan Chen. Transactions on Graphics(TOG), 2007 [pdf]
Mathematical Foundations of Arc Length-Based Aspect Ratio Selection
Procedural Image Processing for Visualization

Xiaoru Yuan, Baoquan Chen
ISVC (1) 2006: 50-59 [pdf]
Mathematical Foundations of Arc Length-Based Aspect Ratio Selection
Perceptually Guided Rendering of Textured Point-based Models

Lijun Qu, Xiaoru Yuan, Minh X. Nguyen, Gary W. Meyer, Baoquan Chen, Jered E. Windsheimer
SPBG 2006: 95-102 [pdf]
Painterly Rendering of Points Abstraction and Rendering of Sparsely Scanned Outdoor Environments

[pdf (8.3MB)], [animation (26.7MB)] , Hui Xu, Nathan Gossett, and Baoquan Chen, Proceedings of the 2004 Eurographics Symposium on Rendering (EGSR'04), Jun 21-23, 2004, Norrköping, Sweden. [pdf]
Sketchy Rendering of Points Stylized Rendering of 3D Scanned Realworld Environments

[ PDF ] , Hui Xu and Baoquan Chen. NPAR 2004, June 7-9, 2004, Annecy, France. [pdf]
Silhouette Rendering of Points Silhouette Rendering for Point-Based Models

[pdf], [animation (17.4MB)] , Hui Xu, Minh X. Nguyen, Xiaoru Yuan and Baoquan Chen, Proceedings of the 2004 Eurographics Symposium on Point-Based Graphics (SPBG'04). Jun 2-4, 2004, ETH Zurich, Switzerland.
scanning various sites ActivePoints: Acquisition, Processing and Navigation of Large Outdoor Environments

[ PDF ] Hui Xu and Baoquan Chen. Technical Report, Computer Science Department, TR.03.02.
Sketch-based Segmentation of Scanned Outdoor Environment Models Sketch-based Segmentation of Scanned Outdoor Environment Models.

[pdf (1.4MB)], , Xiaoru Yuan, Hui Xu, Minh X. Nguyen, Amit Shesh and Baoquan Chen. In Proceeding of the 2nd Eurographics Workshop on Sketch-Based Interfaces and Modeling (SBM'05), Trinity College, Dublin, Ireland, August 28-29, 2005
scanning various sites Knowledge-Based Modeling of Laser-Scanned Trees.

[pdf (5MB)], Hui Xu, Nathan Gossett and Baoquan Chen. In SIGGRAPH'05 Sketches, Los Angeles, CA. July-August, 2005.



     

Publications in Visualization

colorline

Visualization capitalizes upon the human visual perception system to intuit large, complex, and abstract data and perceive hidden patterns and trends to facilitate scientific discovery, medical diagnosis, social study, and digital design, to name a few of its applications. A fundamental focus of our research in visualization is to develop methods to both efficiently and effectively depict large and complicated data sets, thereby providing interactive and intuitive data visualization and exploration. Specifically, we focus on achieving visualization that is accurate, illustrative, interactive, and easy to interface.

Anomaly Detection in GPS data Based on Visual Analyticsi new Anomaly Detection in GPS data Based on Visual Analytics

[ pdf(1.5MB)] Zicheng Liao, Yizhou Yu, Baoquan Chen. 2010 IEEE Conference on Visual Analytics Science and Technology (IEEE VAST), Salt Lake City, October 2010, pp.51-58.
Visualization of High Dynamic Range Data in Geosciences Visualization of High Dynamic Range Data in Geosciences

Xiaoru Yuan, Yingchun Liu, Baoquan Chen, David A. Yuen and Tomas Pergler, Physics of the Earth and Planetary Interiors (PEPI), 2007. Elsevier. (In Press) [pdf]
An Efficient Method for Creating InSaR-like Images An Efficient Method for Creating InSaR-like Images

Xiaoru Yuan, Yingchun Liu, David A. Yuen, Baoquan Chen, Tomas Pergler and Yaolin Shi, Pure and Applied Geophysics (PAGEOPH), 2007. Springer. [pdf]
Visualization Inspired by Light Interference Visualization of Rupture Fault Simulation Inspired by Light Interference

Xiaoru Yuan, Minh X. Nguyen, Yingchun Liu, David A. Yuen, Baoquan Chen and Yaolin Shi IEEE Conference on Visualization 2006 (VIS'06) (Best Poster Candidate), Baltimore, MD. USA. October 29- November 3, 2006.
High Dynamic Range Volume Visualization High Dynamic Range Volume Visualization
Introducing an interactive high dynamic range volume visualization framework (HDR VolVis) for visualizing volumetric data with both high spatial and intensity resolutions, such as 2,048^3 and 16bits per voxel.

[ pdf], [ videos] , Xiaoru Yuan, Minh X. Nguyen, Baoquan Chen and David H. Porter In Proceedings of IEEE Visualization 2005 Minneapolis, MN, USA. Oct 23 - 28, 2005. Best Paper (Application Category)
An expanded version [ PDF] appeared in IEEE Transaction on Visualization and Computer Graphics, vol. 12, no. 4, July/August, 2006.
Volume Cutout Volume Cutout
A novel method and system for cutting out 3D volumetric structures based on simple strokes that are drawn directly on volume rendered images.

[ pdf (5MB)], [ mpeg4 (15MB)] , Xiaoru Yuan, Nan Zhang, Minh X. Nguyen and Baoquan Chen. In Proceeding of Pacific Graphics (PG'05), Macao, China. Oct 12- 14, 2005. (Special issue of The Visual Computer, Springer-Verlag.)
perlin noise legend Paint Inspired Color Mixing and Compositing for Visualization
Color is often used to convey information, and color compositing is often required to visualize multi-variant information. This paper proposes an intuitive method for color compositing so that distinct information is discerniable.
[ PDF ] Nathan Gossett and Baoquan Chen. IEEE Information Visualization, Oct. 10-15, 2004, Austin, TX.
( Technical report with more thorough acknowledgement and implementation details.)

engine surfaces and volume Illustrating Surfaces in Volume
A novel framework for illustrating surfaces in a volume. Surfaces are illustrated by drawing only feature lines, such as silhouettes, valleys, ridges, and surface hatching strokes, and are embedded in volume renderings. This framework promises effective illustration of both surfaces and volumes without occluding or cluttering each other.
[ PDF ] Xiaoru Yuan and Baoquan Chen. Joint EUROGRAPHICS - IEEE TCVG Symposium on Visualization, May 19-21, 2004, Constanz, Germany.

Publications in Sketch-based Modeling and Interfaces

colorline

The early stages of conceptual design by graphic and architectural designers are characterized by ambiguity, imprecision, and fuzzy intention, all difficult to express using the current Computer Aided Design (CAD) tools, which impose constraints of preciseness and are counterintuitive to use. We aim to develop a sketch-based system that supports a sketch representation of an early-stage conceptualization and its later smooth and easy transition to more precise design stages. This development, together with our outdoor scanning research [project site], will ultimately lead to a radically new digital design tool that will accommodate the needs of architectural design in the digital age: design amid the real sites and design by sketching. [ project site]We also explore using sketches as an interface for not only modeling, but also various visualization tasks.

Microsoft Tablet PC SMARTPAPER
A new modeling tool, which capitalizes the newly available Tablet PC technology and provides a traditional pencil and paper experience, but greatly enhances that experience by offering an additional set of key operations, most importantly sketch interpretation and 3D reconstruction.
[ PDF ] SMARTPAPER: An Interactive and User Friendly Sketching System, Amit Shesh and Baoquan Chen. Eurographics 2004, Aug 30-Sep 3, Grenoble, France.
[ PDF ] User Interface Design and Realization of a Design-by-Sketches System, Amit Shesh and Baoquan Chen. Technical Report, Computer Science Department, TR.04.01.
scanning various sites Peek-in-the-Pic: Architectural Scene Navigation from a Single Picture Using Line Drawing Cues.

[ pdf (2MB)], , Amit Shesh and Baoquan Chen. In Proceeding of Pacific Graphics (PG'05), Macao, China. Oct 12- 14, 2005.


Publications in Non-Photorealistic Rendering(NPR)

colorline

Artistic illustration, unlike traditional photorealistic rendering, depicts object characteristics of different importance by using different accuracy and drawing styles. Such non-photorealistic rendering (NPR) not only conveys aesthetics but also provide effective visualization.

Stippling and Silhouettes Rendering in Geometry-Image Space Stippling and Silhouettes Rendering in Geometry-Image Space.

[ pdf], [ mpeg4 (20MB)] , Xiaoru Yuan, Minh X. Nguyen, Nan Zhang and Baoquan Chen. In Proceedings of Eurographics Symposium on Rendering (EGSR'05), page 193-200. Konstanz, Germany. June 29-July 1, 2005.
curly hair Armadillo Inspire: An Interactive Image-Assisted NPR System
INSPIRE is a non-photorealistic rendering (NPR) system that features interactive generation of a wide variety of artistic styles for large geometric data. Inspire also promises animation consistency during object navigation. Comparing with conventional physics-based graphics rendering targeting photorealism, stylized rendering can better depict and highlight geometric features, hence is more effective when used for scientific or medical data visualization.
[ PDF ] Minh X. Nguyen, Hui Xu, Xiaoru Yuan, and Baoquan Chen. Pacific Graphics, Canmore, Alberta, Canada, October 8-10, 2003.


Publications in Operations Using New Geometry Representations:
Polygons, Points, Hybrids, Geometry Images

colorline

Optimized geometry representations can not only speed up graphics processing and rendering, but also facilitate difficult operation and achieving novel effect.

Ray Casting Feature-enhanced Distance Field Raycasting Feature-Enhanced Distance Field

Nan Zhang, Xiaoru Yuan, Baoquan Chen and Huamin Qu IEEE Conference on Visualization 2006 (VIS'06) (Poster). Baltimore, MD. USA. October 29- November 3, 2006.
Texture Splatting TSplatting: Mapping High Quality Textures on Sparse Point Sets

Xiaoru Yuan, Minh X. Nguyen, Lijun Qu, Baoquan Chen and Gary Meyer Submitted to IEEE Transaction on Visualization and Computer Graphics.
Point Simplification by Perception Perceptually Guided Texture Mapping on Points

[ pdf (6.9MB)] , Lijun Qu, Xiaoru Yuan, Minh X. Nguyen, Gary Meyer and Baoquan Chen In Proceeding of the 3rd IEEE/Eurographics Symposium on Point-Based Graphics (PBG06), Pages 95-102. Boston, MA, USA. July 29-30, 2006.
Mesh and Meshless simulation Integrating Mesh and Meshfree Methods for Physics-Based Fracture and Debris Cloud Simulation

[ pdf (3.5MB)] , Nan Zhang, Xiangmin Zhou, Desong Sha, Xiaoru Yuan, Kumar K. Tamma, and Baoquan Chen. In Proceeding of the 3rd IEEE/Eurographics Symposium on Point-Based Graphics (PBG06), Pages 145-154. Boston, MA, USA. July 29-30, 2006.
Geometry Completion and Detail Generation by Texture Synthesis Geometry Completion and Detail Generation by Texture Synthesis.

[ pdf (9MB)], [ mpeg4 (16MB)] , Minh X. Nguyen, Xiaoru Yuan and Baoquan Chen. In Proceeding of Pacific Graphics (PG'05), Macao, China. Oct 12- 14, 2005. (Special issue of The Visual Computer, Springer-Verlag.)
hybrid forward volume rendering Hybrid Forward Resampling and Volume Rendering
The transforming and rendering of discrete objects, such as traditional images (with or without depths) and volumes, can be considered as resampling problem -- objects are reconstructed, transformed, filtered, and finally sampled on screen grids. In resampling practices, discrete samples (pixels, voxels) can be considered either as infinitesimal sample points (simply called points) or samples of a certain size ( splats). Resampling can also be done either forwardly or backwardly in either source domain or target domain. Here we present a framework that features hybrid forward resampling for discrete rendering. Specifically, we apply this framework to enhance image warping (with or without depth) and volumetric splatting. For the latter, methods for efficiently computing a splat's 2D elliptical projection geometry and achieving accurate perspective reconstruction filter have also been developed. The results of our experiments demonstrate both the effectiveness of antialiasing and the efficiency of rendering using this approach.
[ PDF ] [ movies ] IEEE Volume Graphics, Tokyo, Japan, July 7-8, 2003.
Point-Polygon Rdnering System POP: A Hybrid Point and Polygon Rendering System for Large Data
[ project site (Demo+Sample Data) ]
We introduce a simple but important extension to the existing pure point rendering systems. Rather than using only points, we use both points and polygons to represent and render large mesh models. We start from triangles as leaf nodes and build up a hierarchical tree structure with intermediate nodes as points. During the rendering, the system determines whether to use a point (of a non-leaf node) or a triangle (of a leaf node) for display depending on the screen contribution of each node. (Red for points, blue for triangles in the left image.) While the points are used to speedup the rendering for distant objects, the triangles are used to ensure the quality for close objects. We also perform pre-texturing on points and triangles when we build up the tree. Our hybrid representation facilitates effective antialiasing for texture mapping.
[ PDF ] [ Color Plate ] IEEE Visualization 2001.

IBR to Volume Rendering Image-Based Volume Rendering
Volume rendering is considered expensive due to the huge amount of data to be processed. we present a framework of accelerating volume rendering utilizing image-based rendering technique. The first image of the lower row is fully volume rendered, called keyview; the top image is the intermediate novel view by texture mapping of the keyview onto an underlying geometry of the volume; the second image of the lower row is the final novel view by filling red colored holes of the intermediate image through ray-casting. We have demonstrated the effectiveness of our approach by applying it to a real medical system of virtual colonoscopy navigation. We have obtained an order of magnitude speedup over the traditional volume rendering.
Paper
  • Image-Based Rendering of Surfaces from Volume Data
    [ PDF ] , IEEE Workshop on Volume Graphics, 2001.

Publications in 2000-

colorline

Three main thrusts: (1) volume rendering, (2) special hardware design for volume rendering, (3) image-based techniques.

LOD+Sprite LOD-Sprite Technique for Accelerated Terrain Rendering [ project site ]
We present a new rendering technique, termed LOD-sprite rendering, which uses a combination of a level-of-detail (LOD) representation of the scene together with reusing image sprites (previously rendered images). Our primary application is an acceleration technique for virtual environment navigation, especially for terrain rendering in flight simulation (the left image is a typical scene). The LOD-sprite technique can be efficiently implemented in texture-mapping graphics hardware, thus the speedup is substantial by employing this technique.
[ gziped PS ] [ PDF ] , IEEE Visualization'99.

Multi-tetra LOD Representation of Regular Volumes and Iso-surface Construction
We present an algorithm for continuous level of detail representation of regular volumes based on a level of detail framework, that approximates volume data with different levels-of-detail tetrahedra. Conceptually, the framework is generated through a recursive subdivision of the volume data, however, it does not need any explicit storage representation --- the subdivision level relationships can be easily obtained by implicit data structures, thus gaining efficiency while avoiding large data storage. Instead of using a particular level of the LOD-Tetra framework for approximation, an error-based LOD model is employed to recursively fuse a sequence of tetrahedra from different levels. Cares are taken to maintain the topology and the smooth transition between levels during the fusion. Our approach naturally generates smooth isosurfaces and avoids crack problem suffered by the other methods. Experimental results demonstrate the effectiveness of primitive reduction and smooth transition between error threshold boundary. The left image has an error threshold of 0.0 at the left side, while 4.0 at the right side.
Multiresolution Tetrahedral Framework for Visualizing Regular Volume Data [ PS ] [ PDF ] , IEEE Visualization'97, Phoenix, Arizona, Oct. 19-24 1997.

Texture Mapping High Quality and Efficient Texture Mapping
We present an algorithm called FAST (Footprint Area Sampling for Texturing), which is efficient as well as delivers high-quality texture mapping. By utilizing coherence between neighboring pixels, performing prefiltering, and applying an area sampling scheme, we guarantee a minimum number of samples sufficient for effective antialiasing. Unlike existing methods (e.g., MIP-map, footprint assembly), our method performs bilinear instead of trilinear interpolation to avoid over blurring. Our method has been shown to not only deliver as high quality images as adaptive supersampling, but also require lower memory bandwidth of texel access similar to MIP-map, while retaining the same efficiency as footprint assembly.
Footprint Area Sampled Texturing [ PDF ] , IEEE Transactions on Visualization and Computer Graphics, vol. 10, no. 2, Mar/Apr, 2004. pp. 230-240.
Image Warping Forward Perspective Image Mapping [ project site ] [ benchmark images ]
We present a new forward image warping algorithm, which speeds up perspective warping -- as in texture mapping. It processes the source image in a special scanline order instead of the normal raster scanline order. This special scanline has the property of preserving parallelism when projecting to the target image. The algorithm reduces the complexity of perspective-correct image warping by eliminating the division per pixel and replacing it with a division per scanline. The method also corrects the perspective distortion in Gouraud shading with negligible overhead. Furthermore, the special scanline order is suitable for antialiasing using a more accurate antialiasing conic filter, with minimum additional cost. The algorithm is highlighted by incremental calculations and optimized memory bandwidth by reading each source pixel only once, suggesting a potential hardware implementation.
[ gziped PS ] [ PDF ] , IEEE Visualization '99.

3D rotation by shear Image/Volume Rotation Using Shear Transformations
3D volume rotation is important in volume manipulation and registration, however, is expensive to perform. We present a group of methods of decomposing 3D volume rotation into pure 1D, 2D, or 3D shear transformations, resulting in four-pass, three-pass, or even two-pass decompositions. Multiple decompositions give us different choices for different scenery. The simplicity and regularity of shear transformation is especially suitable for parallel hardware implementation.
Papers
  • 3D Volume Rotation Using Shear Transformations
    [ gziped PS ] [ PDF ] , Graphical Models (formerly Graphical Models and Image Processing (GMIP) journal), vol. 62, 2000, pp 308 -- 322.
  • Two-Pass Image and Volume Rotation ,
    [ PDF ] , IEEE Workshop on Volume Graphics, 2001.


Walk Into Images Navigating Through Sparse Views [ project site ]
We investigate two problems involved in creating animation from static image/images. We first extend the work of "TIP" (in SIGGRAPH'97) to increase the freedom of modeling, thus better approximation of the underlying scene structure. Further, we study a situation where the camera is moved further into the scene and sequence of shots are taken along the path. This is opposed to previous panorama scene creation, in which pictures are obtained by rotating camera 360 degree, but fixing camera position.
[ PDF ] , VRST (Symposium on Virtual Reality Software and Technology) '99.

Cube-2 and VolumePro Architecture Design for Volume Processing and Universal 3D Rendering
Coded "Cube", this project is to design and implement a special-purpose volume rendering accelerator for the real-time visualization of high-resolution volumetric datasets. Cube-4 design has been adopted by MECO and JRC. The Mitsubishi Electric VolumePro boards, based on Cube design, have been available since the second quarter of 1999. The left is the picture of Cube-2 chip and VolumePro board. The latest architecture, Cube-5, performs arbitrary parallel and perspective projections of high-resolution datasets at true real-time frame rates. More importantly, it aims to handle multiple overlapping volumes, and the mixed scene of volumes and traditional geometric primitives, such as polygons. Furthermore, Cube-5 can be used to accelerate image-based rendering and other techniques because of Cube-5's powerful functionality of interpolation.
Papers
  • Real-Time Volume Rendering
    [ gziped PS ] [ PDF ] , accepted to Special Issue on 3D Imaging of the International Journal of Imaging Systems and Technology.
  • Adaptive Perspective Ray Casting
    [ PS ] [ PDF ] , IEEE 1998 Symposium on Volume Visualization, Oct. 19-20, 1998, Research Triangle Park, North Carolina.
  • High-Quality Volume Rendering Using Texture Mapping Hardware
    [ PS ] [ PDF ] ( color images [ PS ] [ PDF ] ) , 1998 Eurographics/Siggraph Workshop on Graphics Hardware, Aug. 31 - Sep. 1, 1998, Lisbon, Portugal.
Patents
  • Two patents awarded in the field of volume graphics, Co-Inventor.


DSP for Volume DSP Accelerated Volume Rendering on PC
As real-time volume rendering requires a very high computing power and memory bandwidth, many efforts are under-taken on how to reach this goal. In this project, we implement a DSP (Digital Signal Processing) based volume renderer. We employ TI (Texas Instruments)'s latest multiprocessor DSP, TMS320C80, with one master and four parallel processors. We have studied ways to accelerate volume rendering, with considerations especially on full exploration of external memory bandwidth.
[ CVC Techniqual Report TR.990107 ] , Center for Visual Computing, SUNY at Stony Brook.

Texture Synthesis Texture Synthesis of Wood and Stony Wall and Floor
In this early project, we have synthesized several kinds of textures: wood, stony wall and floor. Texture patterns can be controlled by adjusting some simple and intuitive parameters.
[ Computer Generated Textures Used in Architecture ] International Conference on Modeling, Simulating & Control, MSC'93, Chengdu, China, Oct. 13-15, 1993, Vol.2 pages 71-78.
[ Computer Generated Textures of Surfaces for Many Kinds of Wall and Floor ] National Symposium on Image and Graphics conference, NSIG'94, Chengdu, China, April 19-23, 1994, Vol.2

* Back to my home page.