中国科技大学《计算机图形学》暑期课程
USTC Summer School 2013 (001M0601)
图形与几何计算实验室 (Graphics&Geometric Computing Laboratory)
中国科学技术大学 (University of Science and Technology of China)
|
时间 |
授课老师 |
课程题目 |
|
7月3日 星期三 |
08:30-08:50 |
刘利刚 |
课程介绍 |
08:50-10:00 |
刘利刚 |
几何建模与处理及计算机图形学进展 |
|
10:15-11:45 |
童晶 |
从深度相机到三维打印--原理、应用、研究 |
|
15:00-16:00 |
张举勇 |
建筑几何研究进展(1) |
|
16:15-17:15 |
张举勇 |
建筑几何研究进展(2) |
|
7月4日 星期四 |
08:30-10:00 |
陈中贵 |
重心Voronoi图与最优Delaunay剖分及其应用(1) |
10:15-11:45 |
陈中贵 |
重心Voronoi图与最优Delaunay剖分及其应用(2) |
|
15:00-16:00 |
李新 |
基于T样条的几何造型(1) |
|
16:15-17:45 |
李新 |
基于T样条的几何造型(2) |
|
7月5日 星期五 |
08:30-10:00 |
刘永进 |
网格曲面上基于测地度量的Voronoi图构建 |
10:15-11:45 |
周世哲 |
Animated Line drawing and pattern-aware curve decoration |
|
15:00-16:00 |
邓建松 |
等几何分析(1) |
|
16:15-17:45 |
邓建松 |
等几何分析(2) |
|
7月6日 星期六 |
08:30-10:00 |
陈为 |
信息可视化与可视分析(1) |
10:15-11:45 |
陈为 |
信息可视化与可视分析(2) |
|
15:00-16:00 |
陈雪锦 |
基于图像的三维建模(1) |
|
16:15-17:45 |
陈雪锦 |
基于图像的三维建模(2) |
|
7月7日 星期日 |
08:30-10:00 |
吴春林 |
Variational methods for image processing and computer graphics(1) |
10:15-11:45 |
吴春林 |
Variational methods for image processing and computer graphics(2) |
|
15:00-16:00 |
杨周旺 |
压缩感知与几何稀疏建模(1) |
|
16:15-17:45 |
杨周旺 |
压缩感知与几何稀疏建模(2) |
|
7月8日 星期一 |
08:30-10:00 |
张磊 |
基于互联网图像/视频的图形学研究 |
10:15-11:45 |
刘利刚 |
全局思考、局部操作的方法 |
|
15:00-16:00 |
Seungyong Lee |
Image deblurring (1) |
|
16:15-17:15 |
Seungyong Lee |
Image deblurring (2) |
|
7月9日 星期二 |
08:30-10:00 |
Wotao Yin | Compressed sensing, sparse optimization with big data |
10:15-11:45 |
Jorg Peters |
Modeling with rational splines |
|
15:00-16:00 |
Seungyong Lee |
Image stylization (1) |
|
16:15-17:15 |
Seungyong Lee |
Image stylization (2) |
|
7月10日 星期三 |
08:30-10:00 |
Niloy Mitra |
Structure-aware geometry processing (1) |
10:15-11:45 |
Niloy Mitra |
Structure-aware geometry processing (2) |
|
15:00-16:00 |
Jorg Peters |
Subdivision algorithms (1) |
|
16:15-17:15 |
Jorg Peters |
Subdivision algorithms (2) |
|
17:15-17:35 |
刘利刚 |
课程总结 |
Jorg Peters, University of Florida, USA
http://www.cise.ufl.edu/~jorg/
Dr. Jorg Peters is Professor of Computer and Information Sciences at
University of Florida. He is interested in representing, analyzing and
computing with geometry. To this end he has developed new tools for
free-form modeling and design in spline, Bezier, subdivision and implicit
representations. He is heading the TIPS project to enable surgeon-educators
to author VR-based simulations with force feedback.
Dr. Peters obtained his Ph.D. in 1990 in Computer Sciences from the
University of Wisconsin, Carl de Boor advisor. In 1991 and 1992, Dr Peters
held positions at the IBM T. J. Watson Research Center and Rensselaer
Polytechnic Institute before moving to the computer science department of
Purdue University. In 1994, Dr. Peters received a National Young
Investigator Award. He was tenured at Purdue University in 1997 and moved to
the University of Florida in 1998 where he became full professor.
Dr. Peters serves as associate editor for the journal CAGD, APNUM, ACM ToG,
GMOD and served on various program committees as well as chair of the SIAM
interest group on geometric design. His students have built such useful
tools as BezierView and TIPS.
Niloy Mitra, University College London (UCL), UK
http://www0.cs.ucl.ac.uk/staff/n.mitra/index.html
Niloy J. Mitra is an associate professor (Reader) in the Department of
Computer Science at University College London (UCL). Earlier, he co-founded
the Geometric Modeling and Visualization Center (GMSV) center at KAUST. He
received his Ph.D. degree and Masters in Electrical Engineering from
Stanford University. His research interests include shape understanding,
fabrication-aware design, geometric modeling, recreational art, and computer
graphics in general.
Seungyong Lee, Pohang Univ. of Sci. & Tech. (POSTECH),
Korea
http://www.postech.ac.kr/~leesy/
Seungyong Lee is a professor of computer science and engineering at the
Pohang University of Science and Technology (POSTECH), Korea. He received
the PhD degree in computer science from the Korea Advanced Institute of
Science and Technology (KAIST) in 1995. From 1995 to 1996, he worked at the
City College of New York as a postdoctoral research associate. Since 1996,
he has been a faculty member of POSTECH, where he leads the Computer
Graphics Group. From 2003 to 2004, he spent a sabbatical year at MPI
Informatik in Germany as a visiting senior researcher. From 2010 to 2011, he
worked at Adobe Research in Seattle as a visiting professor. His current
research interests include image and video processing, non-photorealistic
rendering, 3D surface reconstruction, and graphics applications.
Wotao Yin, University of California, Los Angeles,
USA
http://www.caam.rice.edu/~wy1/
Wotao Yin is a professor with Department of Mathematics at UCLA. His
research interests lie in computational optimization and its applications in
image processing, machine learning, medical imaging, and other inverse
problems. He received his B.S. in mathematics from Nanjing University in
2001, and then M.S. and Ph.D. in operations research from Columbia
University in 2003 and 2006, respectively. During 2006-2013, he held
positions as assistant and associate professors at Rice University. He won
NSF CAREER award in 2008 and Alfred P. Sloan Research Fellowship in 2009.
His recent work has been in optimization algorithms for large-scale and
distributed signal processing and machine learning problems..
陈中贵,厦门大学
http://59.77.0.69/~zgchen/
厦门大学信息科学与技术学院计算机科学系助理教授,硕士生导师。2009年毕业于浙江大学数学系,获理学博士学位。2009年至2010年于香港大学计算机系从事博士后研究。研究兴趣包括数字几何处理、计算几何等。
张磊,北京理工大学
http://cs.bit.edu.cn/zhanglei
北京理工大学计算机学院讲师,硕士生导师。研究方向为计算机图形学、图像与视频处理。分别于2004年和2009年在浙江大学数学系获得学士和博士学位。2009年9月至2011年12月在西安交通大学电信学院从事博士后研究工作。2011年12月加入北京理工大学计算机学院。2012年9月聘为硕士生导师。2013年1月入选“北京理工大学优秀青年教师资助计划”。在Siggraph
Asia以及ACM TOG、IEEE TVCG、CGF等国际著名会议和期刊发表SCI论文10余篇。目前作为课题负责人主持国家自然科学青年基金和北京市自然科学基金面上项目各一项,作为子课题负责人参加国家自然科学基金重点项目、863计划、武器装备预研项目等课题。
吴春林,南开大学
Dr. Wu obtained his Ph.D degree from University of Science and Technology of
China in 2006. After taking several Research Fellow positions, he joined
Nankai University in 2012 as an associate professor. His research interests
are in mathematical methods and algorithms in image processing and computer
graphics. Dr. Wu has published nearly 20 research papers including several
in top journals such as SIAM J. Imaging Sciences and ACM TOG.
Title: Structure-aware geometry processing
Lecturer: Niloy Mitra, UCL, UK
Abstract:
Shape structure is about the arrangement and relations between shape parts.
Structure-aware shape processing goes beyond local geometry and low level
processing, and analyzes and processes shapes at a high level. It focuses
more on the global inter and intra semantic relations among the parts of
shape rather than on their local geometry. With recent developments in easy
shape acquisition, access to vast repositories of 3D models, and
simple-to-use desktop fabrication possibilities, the study of structure in
shapes has become a central research topic in shape analysis, editing, and
modeling. A whole new line of structure-aware shape processing algorithms
has emerged that base their operation on an attempt to understand such
structure in shapes. The algorithms broadly consist of two key phases: an
analysis phase, which extracts structural information from input data; and a
(smart) processing phase, which utilizes the extracted information for
exploration, editing, and synthesis of novel shapes. Our goal is to both
give the practitioner an overview of available structure-aware shape
processing techniques, as well as identify future research questions in this
important, emerging, and fascinating research area.
Title: Subdivision and Surfaces
Lecturer: Jorg Peters, University of Florida, USA
Abstract:
Subdivision is a conceptually simple approach to creating smooth shape from
faceted geometry. But subdivision is more than just mesh refinement. The
underlying refinement of functions, box splines in particular, and the
interpretation of subdivision surfaces as splines with singularities help
understanding the rules, uses and limitations of subdivision. The lectures
will leverage and complement the easily available sources on subdivision for
graphics and geometry and explain its relation to surface generation and
computing on surfaces.
Title: Image Deblurring
Lecturer: Seungyong Lee, POSTECH, Korea
Abstract:
Motion blur is a common artifact that produces disappointing blurry images
with inevitable information loss. It is caused by the nature of imaging
sensors that accumulate incoming lights for an amount of time to produce an
image. During exposure, if the camera sensor moves, a motion blurred image
will be obtained. Image (motion) deblurring is a computational process to
remove motion blurs from a blurred image to obtain a sharp latent image.
This lecture will first introduce the problem definition, basic approach,
and recent research trends of image deblurring, and then present research
results of POSTECH on image deblurring, such as fast motion deblurring, text
deblurring, and video deblurring.
Title: Image Stylization
Lecturer: Seungyong Lee, POSTECH, Korea
Abstract:
In contrast to photo-realistic image synthesis, which is a common goal of
computer graphics, non-photorealistic rendering targets to create
expressive, artistic, and interpretative images. Image stylization processes
an input image to produce a variety of stylized images with intended
abstraction. This lecture introduces recent research results of POSTECH on
image stylization, such as line drawings of images, image abstraction, and
directional stippling (hedcut illustration). Research results of POSTECH on
3D non-photorealistic rendering, where the inputs are 3D models with
geometric information, will be briefly introduced as well.
Title: Compressed sensing, sparse optimization with
big data
Lecturer: Wotao Yin, UCLA, USA
Abstract:
Sparse optimization has found interesting applications in many
data-processing areas such as compressed sensing, machine learning, signal
processing, medical imaging, finance, etc. After reviewing compressed
sensing and sparse optimization, this talk then introduces novel algorithms
tailored for very large scale sparse optimization problems with terabytes of
data. Besides the typical complexity analysis, we analyze the overhead due
to parallel and distributed computing. Numerical results are presented to
demonstrate the scalability of the parallel codes for handling terascale
problems on clusters and Amazon EC2.
Title: 信息可视化与可视分析
Lecturer: 陈为,浙江大学
Abstract:
该课程将介绍可视的基本概念与原理、信息可视化的基本方法,以及可视分析的愿景。主要内容包括:信息的表示、可视映射、可视化方法、可视化中的交互、可视分析循环等。配合以大量案例分析。
Title: 3D Modeling from images (基于图像的三维建模)
Lecturer: 陈雪锦,中国科学技术大学
Abstract:
Image-based modeling is one of the hottest topics in Computer Graphics. An
image is the projection of a 3D scene to a 2D plane with certain projection
settings. In this talk, I will first introduce perspective projection model,
which is most close to the real camera model. Second, how to recover the
camera parameters (projection matrix) from images will be introduced. The
third part is to reconstruct the 3D structure from images. The structure can
be represented as 3D point cloud (Structure from Motion), depth map and
surface model (Stereo) or concise outlines (image-based modeling). As a
special type of images, sketch has been studied to represent design concept.
Finally, I will introduce my work on sketch-based modeling.
Title:
重心Voronoi图与最优Delaunay剖分及其应用
Lecturer: 陈中贵,厦门大学
Abstract:
重心Voronoi图(CVT)由于其优良的几何性质在很多领域都有广泛的应用。近几年来,关于CVT性质的研究以及其在不同区域、不同度量上的快速计算方法也成为图形学研究的一个热点。本次课程将介绍CVT的基本性质和计算方法,延伸到带容积约束的重心Voronoi图以及其对偶结构—最优Delaunay剖分(ODT)的计算,并讨论CVT和ODT在网格生成和蓝噪声采样等方面的应用。
Title: 等几何分析
Lecturer: 邓建松,中国科技大学
Abstract:
等几何分析(isogeometric analysis, IGA)是一种与传统的有限元分析在代码框架上完全兼容的计算机辅助工程(CAE)技术。其核心是对分析过程中的网格和逼近,采用一种统一的几何描述,这样可以有效避免网格生成的繁琐性,并且不会出现由于求解区域的逼近而导致的误差,从而使“设计-分析”过程达到更高精度和更加紧密的结合。本课程将从最简单的算例开始,讲解IGA的起源、框架和效果,并且给出应用T网格上的样条进行自适应IGA的算法。
Title: 基于T样条的几何造型
Lecturer: 李新,中国科技大学
Abstract:
本课程主要介绍一些最新的具有局部细分能力的高阶自由曲面造型技术,包括T网格上的多项式样条,层次B样条,LR样条和T样条。
Title: 网格曲面上基于测地度量的Voronoi图构建
Lecturer: 刘永进,清华大学
Abstract:
Voronoi图是自然科学中得到广泛研究的几何工具之一。本课程介绍计算几何中关于Voronoi图的基本定义,并着重分析近年来计算机图形学中广泛使用的三角网格曲面上Voronoi图的构建方法。该构建方法的难点在于所采用的测地度量所带来的与欧氏空间中Voronoi图截然不同的拓扑和组合性质。以网格曲面上采用测地度量的Voronoi图为基本几何工具,最后介绍该几何工具在计算机图形学与模式识别中的几个典型应用。
Title:
从深度相机到三维打印--原理、应用、研究
Lecturer: 童晶,河海大学
Abstract:
随着深度相机技术的走向普及,使得一般用户也能简单、高效、廉价地创建数字三维模型。随着三维打印技术的快速发展,人们不仅可以得到虚拟的数字化模型,也能类似打印二维照片,生成实物的三维模型。本课程将介绍深度相机、三维打印设备的原理,并列举其在工业设计、加工制造、生物医学、文化创意等诸多领域的应用。低成本三维扫描、三维打印技术中亟待解决的问题,也为计算机图形学的理论及应用研究提供了新的机遇。
Title: Variational methods for image processing and
computer graphics
Lecturer: 吴春林,南开大学
Abstract:
In this lecture I will introduce variational methods for image processing
and computer graphics. In recent years variational methods have been proven
successful in imaging sciences. Both fundamental models in image processing
and generalizations in computer graphics applications will be introduced.
Title: 压缩感知与几何稀疏建模
Lecturer:
杨周旺,中国科技大学
Abstract:
课程内容主要包括两个方面:
(1) 压缩感觉的理论与算法,介绍压缩感知的相关理论,压缩感知模型的求解算法及其应用条件。
(2) 几何稀疏建模方法及应用,介绍稀疏建模方法(即如何获得信号的稀疏表达)在几何信号处理中的若干应用。
Title: 建筑几何研究进展
Lecturer:
张举勇,中国科学技术大学
Abstract:
建筑几何本质是通过计算几何,几何分析,数学优化等技术来解决建筑领域中一些具有难度的设计、构造与分析等问题。近年来,建筑几何作为新兴的交叉学科吸引了来自计算机图形学,建筑,几何分析等领域研究人员的浓厚兴趣。这促进了建筑几何学科的快速发展,相关的建筑几何咨询公司与开源软件也推动了传统的建筑设计行业,如埃菲尔铁搭的改建中就运用了建筑几何的最新研究成果。本课程主要介绍近来建筑几何一些研究进展,包括自由曲面的平面四边形化,形状空间探索,曲面玻璃的应用等课题。
Title: 基于互联网图像/视频的图形学研究
Lecturer: 张磊,北京理工大学
Abstract:
互联网技术的发展和数码摄像设备的普及使得图像/视频的获取和分享变得非常容易,由此形成了以海量、多源、异构图像/视频数据聚合为代表的大数据资源,给包括计算机图形学在内的许多学科带来了新的挑战和机遇。本课程将主要介绍近几年计算机图形学领域围绕互联网图像/视频开展的研究工作,重点介绍大规模数据聚合在图像/视频特征分析、内容编辑、知识理解等方面产生的新问题,以及在计算机图形学的几何建模、绘制及其应用中产生的新方法。此外,还将介绍我们课题组在该领域开展的若干代表性研究工作。
Title:
Animated Line drawing and pattern-aware curve decoration
Lecturer: 周世哲,中国科技大学
Abstract:
Recent research works try to assist human's handwriting and drawing process
by guiding the curve shape with abstracted structure sketches and enhancing
low-level details with stroke stylization. We will discuss about several
methods on how to construct abstractions of line drawings by progressive
simplification and geometric fitting and their applications on inverse
animation of a plausible drawing process. In terms of curve decoration, we
will look into several synthesis-based line stylization methods, which owns
various advantages including distortion-free, exemplar pattern-awareness,
structure-preservation, etc. Besides novel workflow and optimization,
synthesis speed issues dealt with a parallel implementation will also be
discussed.
Title: 几何建模与处理及计算机图形学进展
Lecturer: 刘利刚,中国科技大学
Abstract:
随着计算机图形学的快速发展、数字摄像机和扫描工具等获取三维信息的技术手段不断进步和成熟,以及三维图形处理硬件和计算机性能的飞速提高,三维几何模型的传播和应用得到广泛的推广和使用,已成为继声音、图像和视频之后的第四种多媒体数据类型。我们将介绍最近10年来数字几何处理的主要问题、方法及进展,
并且介绍最近的计算机图形学的进展。
Title: 从形状理解、分析到建模
Lecturer: 刘利刚,中国科技大学
Abstract:
近年来三维模型获取和生成的手段日新月异,但三维内容生成仍旧是计算机图形学领域的难点。如何批量生成多样的三维模型,以快速构建、丰富三维虚拟场景(如城市、战场等),是当前几何建模的核心问题之一。随着互联网上三维模型数量和质量的不断提高,如何分析和理解三维模型集合中蕴含的语义信息,并借助该语义信息自动合成新的三维模型,已逐渐成为图形学的最新热点。本次报告首先介绍基于同类物体三维模型集合的联合语义分析。基于分析得到的语义信息,我们介绍若干种语义驱动的三维模型生成方法。
References:
State-of-the-art papers in computer graphics.
Readings:
Various
journal papers, conference papers, or WWW materials as appropriate.
Computer Program Documentation Standards
Advices on Researches:
Mesh Models:
Mesh library on the internet:
Model formats:
OpenGL programming:
GUI toolkits:
Renders:
Useful coding related sites on the internet:
Send any comments or
suggestions to Prof. Ligang Liu (lgliu@ustc.edu.cn)
Copyright © 2013, Ligang Liu