第六届中国科技大学《计算机图形学》暑期课程
USTC Summer
School 2017 (001M0601)
Advances in Computer Graphics
(计算机图形学前沿进展)
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)
|
|
|
|
Announcements |
-
2017年7月9日:暑期课程视频
-
2017年7月7日:中科大的选课的本科生的课程考核要求(点击进入),deadline:2017年8月27日。
-
2017年6月15日:已通过SmartChair系统向成功注册的学员发送邮件。请成功注册课程的学员仔细查看课程注意事项(点击查看)。
-
注册人数已满,不再接受新注册。
-
2017年5月30日:参加课程注意事项(点击查看)。
-
2017年5月30日:已通过系统向所有选课学员发送了选课通知,请各位选课学员查看邮箱确认是否已成功选课,请注意查看信箱。
-
2017年5月29日:注册人数已满,不再接受注册。
-
2017年5月9日:参加暑期课程的学员食宿自理。中国科技大学东校区周边酒店信息下载(
供参考,具体信息请直接联系酒店)。由于科大暑期活动很多,周边住宿会非常紧张。请外地学员及早自行预订住宿。
-
2017年5月9日:课程地点在中国科技大学东区的理化大楼,靠近科大东区南门(太湖路)附近,点击查看地图位置。
-
2017年5月4日:课程开放注册。点击注册(注册之前请务必仔细查阅“课程注册说明文档”)。
注册名额有限。名额满后,即不再开放注册。
-
2017年4月15日:注册系统将在5月初开放。名额有限,敬请关注。
-
2017年2月26日:今年的暑期课程时间定为2017年7月3日至7月7日共5天。授课计划初步确定,今年的课程将继续完全免费。
|
|
课程介绍: |
-
《计算机图形学前沿进展》(课程编号:001M06)为中国科技大学暑期学期的课程。课程由数学科学学院中科大图形与几何计算实验室(GCL)的刘利刚老师及国内外学者共同授课。本年度课程的主题为“3D几何感知与建模、
虚拟现实、机器人与机器学习”。若对计算机图形学中的几何处理不太熟悉的同学,可提前看一下
刘利刚老师开设的本科生课程《计算机图形学》(2013,2014,2015,
2016,2017)和研究生课程《数字几何处理》的主页(其中有较完善的课程课件提供下载
)。
-
该课程为中国科学技术大学全校性公共选修课程,面向应用数学、计算机科学、信息科学等相关专业的学生,欢迎数学学院、少年班学院、信息学院、计算机学院等学院的本科生高年级学生和研究生来选课
。
-
若本校的本科生需要该课程的学分,需要在校教务系统中进行选课。
-
该课程以介绍计算机图形学领域的最新的研究成果及进展为主,同时兼顾本科生也会介绍该领域的一些基本问题和研究方向,只要有《线性代数》、《微积分》、《解析几何》、《微分几何》等课程知识的学生都可以听懂。
-
本次课程的内容涵盖几何建模、网格化技术、形状的感知分析、点云处理、深度相机、细分造型技术、3D打印、虚拟现实
、机器人、深度学习等内容,内容丰富和前沿,是了解计算机图形学前沿和未来方向的非常难得的机会。
-
上课时间:2017年7月3日至7月7日
-
上课地点:中国科学技术大学东区理化大楼西三报告厅
-
学分:2
|
|
课程安排: |
时间 |
授课老师 |
课程题目 |
7月3日
星期一
City& Modeling |
08:30-08:40 |
刘利刚 |
课程介绍 |
08:40-10:10 |
陈宝权 |
城市场景三维感知与分析 |
10:25-11:55 |
Long Quan |
Capturing the World with Cameras! |
14:30-16:00 |
王程 |
大规模移动激光扫描三维点云获取与处理 |
16:15-17:45 |
Hongbo Fu |
Sketch-based 3D Modeling |
7月4日
星期二
VR&Face |
08:30-10:00 |
周而进 |
深度学习下人脸识别的应用与挑战 |
10:15-11:45 |
张举勇 |
三维人脸重建及其应用 |
14:30-16:00 |
谢国富 |
3D VR视频合成及应用 |
16:15-17:45 |
傅孝明 |
Real Walking Mapping Computation and Its
Applications in VR |
7月5日
星期三
Learning |
08:30-10:00 |
林宙辰 |
Low-Rank Subspace Clustering |
10:15-11:45 |
沈小勇 |
Awesome Applications of Deep Learning in Computer
Vision |
14:30-16:00 |
韩晓光 |
深度学习在三维重建及建模中的应用 |
16:15-17:45 |
刘利刚 |
面向制造的几何设计与优化 |
7月6日
星期四
Graphics&
GPU |
08:30-10:00 |
童欣 |
Data-Driven graphics |
10:15-11:45 |
邵天甲 |
基于常见图像类型的三维建模 |
14:30-16:00 |
黄晓煌 |
计算机图形学与GPGPU在“酷家乐”里的实践 |
16:15-17:45 |
Renjie Chen |
Parallel geometry processing on GPU |
7月7日
星期五
Robotics |
08:30-10:00 |
卢策吾 |
Autonomous Machine powered
by Computer Vision |
10:15-11:45 |
郭诗辉 |
面向机器人的动态结构设计 |
14:30-16:00 |
宋鹏 |
智能机器人视觉感知中的三维几何分析与处理 |
16:15-17:45 |
Paul Kry |
Physics Based Computer
Animation Fundamentals |
|
授课教师及课程介绍: |
|
-
Paul G.
Kry, McGill University, Canada
http://www.cs.mcgill.ca/~kry
Paul G. Kry received his B.Math. in computer science with electrical
engineering electives in 1997 from the University of Waterloo, and
his M.Sc. and Ph.D. in computer science from the University of
British Columbia in 2000 and 2005. He spent time as a visitor at
Rutgers during most of his Ph.D., and did postdoctoral work at INRIA
Rhône Alpes and the LNRS at Université René Descartes. He is
currently an associate professor at McGill University, where he
heads the Computer Animation and Interaction Capture Laboratory. His
research interests are in physically based animation, including
deformation, contact, motion editing, and simulated control of
locomotion, grasping, and balance. He co-chaired ACM/EG Symposium on
Computer Animation in 2012, Graphics Interface in 2014, and served
on numerous program committees, including ACM SIGGRAPH, SIGGRAPH
ASIA, Eurographics, ACM/EG Symposium on Computer Animation, Pacific
Graphics, and Graphics Interface. He is currently an associate
editor for Computer Graphics Forum, and for Computers and Graphics.
In 2014, Paul Kry became the president of the Canadian Human
Computer Communications Society, the organization which sponsors the
annual Graphics Interface conference, and since 2016 he is a
director at large on the ACM SIGGRAPH executive committee.
-
Title:
Physics Based Computer Animation Fundamentals Abstract:
This 90 minute course will introduce the main concepts of
physically based computer animation, with a focus on elastic and
rigid body systems. We will examine different numerical integration
techniques and see how the eigenvalue decomposition of a linear
system can be used to understand the long term behavior of different
stepping methods. We will look at real examples of larger stiff
systems that benefit from iterative linear solvers, and see how
constraints and constraint stabilization work as an alternative.
Collision detection, collision response, contact constraints and
friction will also be covered. Various concepts will be demonstrated
with interactive 2D examples. Additional resources for future study
will be included throughout the course. To conclude I will briefly
point out several advanced topics that build on this material.
|
|
-
Long
QUAN,香港科技大学(HKUST)
https://www.cse.ust.hk/~quan/
Long QUAN is a Professor of the Department of Computer Science and
Engineering at HKUST. He received his PhD in 1989 in Computer
Science from INPL, France. He became a permanent researcher at CNRS
in 1990 and was appointed to INRIA in Grenoble, France. He joined
HKUST in 2001, and was the founding director of the HKUST Center for
Visual Computing and Image Science. He is a Fellow of the IEEE
Computer Society. He founded the altizure.com.
He works on vision geometry, 3D reconstruction and image-based
modeling. He was voted one of the HKUST Best Ten Lecturers in 2004
and 2009. He has served as an Associate Editor of IEEE Transactions
on Pattern Analysis and Machine Intelligence, and is a Regional
Editor of Image and Vision Computing Journal. He is on the editorial
board of the International Journal of Computer Vision, Electronic
Letters on Computer Vision and Image Analysis, Machine Vision and
Applications, and Foundations and Trends in Computer Graphics and
Vision. He was a Program Chair of IAPR International Conference on
Pattern Recognition 2006 Computer Vision and Image Analysis, a
Program Chair of ICPR 2012 Computer and Robot Vision, and a General
Chair of IEEE International Conference on Computer Vision (ICCV)
2011.
-
Title:
Capturing the World with Cameras! Abstract:
Professor Quan leads a team that uses photographs and deep
visual learning technologies to produce complete 3D models of all
types of locations on Earth. In this talk, he reviews the
developments in computer vision and machine learning over the past
three decades. He also turns the focus on recent exciting work in
deep visual learning and 3D reconstruction using photographs. Here,
he showcases the approach using case studies of both large scale of
hundreds of square kilometers from drone photographs, and also the
small-scale 3D objects from smart phone photographs. He also
demonstrates the online cloud platform and portal www.altizure.com
with its crowed-sourced Altizure Earth, developed and funded by the
HKUST team, rivaling the popular Google earth!
|
|
|
|
|
|
|
|
-
林宙辰,北京大学
http://www.cis.pku.edu.cn/faculty/vision/zlin/zlin.htm
Zhouchen Lin received the Ph.D. degree in applied mathematics from
Peking University in 2000. He is currently a Professor at Key
Laboratory of Machine Perception (MOE), School of Electronics
Engineering and Computer Science, Peking University. He is also a
Chair Professor at Northeast Normal University and a guest professor
at Beijing Jiaotong University. He was a guest professor at Shanghai
Jiaotong University and Southeast University, and a guest researcher
at Institute of Computing Technology, Chinese Academy of Sciences.
His research areas include image processing, computer vision,
pattern recognition, machine learning, and numerical optimization He
is an associate editor of IEEE T. Pattern Analysis and Machine
Intelligence and International J. Computer Vision and an area chair
or senior program committee member of CVPR 2014, ICCV 2015, NIPS
2015, AAAI 2016, CVPR 2016, IJCAI 2016, AAAI 2017, and AAAI 2018. He
is an IAPR Fellow.
-
Title:
Low-Rank Subspace Clustering Abstract:
Low-rank modeling are emerging mathematical tools dealing with
uncertainties of real-world visual data. Leveraging on the
underlying structure of data, low-rank modeling approaches have
achieved impressive performance in many visual learning tasks. In
this tutorial, I will introduce in detail the latest subspace
clustering techniques. For low-rankness based approaches, I will
present some representative subspace clustering models, analyze
their theoretical properties, such as exact recovery, closed-form
solutions and block-diagonal structure, and present applications in
various real problems in computer vision.
|
|
-
Hongbo
Fu, City University of Hong Kong
http://sweb.cityu.edu.hk/hongbofu/
Hongbo Fu is an Associate Professor in the School of Creative Media,
City University of Hong Kong. Before joining CityU, he had
postdoctoral research trainings at the Imager Lab, University of
British Columbia, Canada and the Department of Computer Graphics,
Max-Planck-Institut Informatik, Germany. He received the PhD degree
in computer science from the Hong Kong University of Science and
Technology in 2007 and the BS degree in information sciences from
Peking University, China, in 2002. His primary research interests
fall in the fields of computer graphics and human computer
interaction. His research has led to more than 50 scientific
publications, including over 10 technical papers presented at
SIGGRAPH or SIGGRAPH Asia. His recent works have received the Best
Demo awards at the Emerging Technologies program, SIGGRAPH Asia in
both 2013 and 2014, and the Best Paper award from CAD/Graphics 2015.
He was the Organization Co-Chair of Pacific Graphics 2012, the
Program Chair/Co-chair of CAD/Graphics 2013, SIGGRAPH Asia 2013
(Emerging Technologies), SIGGRAPH Asia 2014 (Workshops) and
CAD/Graphics 2015, and the Conference Chair of SIGGRAPH Asia 2016.
He is currently on the SIGGRAPH Asia Conference Advisory Group. He
has served as an Associate Editor of The Visual Computer
(2013-2016), Computers & Graphics, and Computer Graphics Forum.
-
Title:
Sketch-based 3D Modeling Abstract:
3D modeling has been one of the fundamental research topics in
computer graphics and computer vision. While at least hundreds of 3D
modeling techniques have been proposed in the past decades, most of
the existing techniques have a high learning curve and are limited
to professionals. On the other hand, the emerging applications such
as Augmented Reality and 3D printing demand 3D modeling tools that
are easy to learn and use. Sketch-based interfaces potentially
enable such modeling tools, since sketches as simple forms can
depict complicated ideas. In this talk, I will give an overview of
sketch-based 3D modeling and focus more discussions on my own
attempts and the state-of-the-art works.
|
|
-
卢策吾,上海交通大学
https://cvsjtu.wordpress.com
Cewu Lu (卢策吾) is a Research Professor at Shanghai Jiao Tong
University (SJTU) and leader of Vision Machine and Intelligence
Group. Before he joined SJTU, he was a research fellow at Stanford
University AI lab working under Prof. Fei-fei Li and Prof. Leonidas
J. Guibas . He was a Research Assistant Professor at Hong Kong
University of Science and Technology with Prof. Chi Keung Tang . He
got the his PhD degree from The Chinese University of Hong Kong,
supervised by Prof. Jiaya Jia. He was selected as the 1000 Overseas
Talent Plan (Young Talent) (中组部青年千人计划) by Chinese central
government. He has published about 30 CCF-A papers (including CVPR/ICCV/TPAMI/IJCV).
He is one of core technique member in Stanford-Toyota autonomous car
project (斯坦福-丰田,无人车项目). Some of his proposed algorithms have been
used as a basic tool function in OpenCV (such as decolor.cpp). He
has one Best Paper Award at the Non-Photorealistic Animation and
Rendering (NPAR) 2012 and one most cited paper among all papers in
SIGGRAPH recent 5 years. He serves as an associate editor for
Journal gtCVPR and reviewer for Journal TPAMI and IJCV. His research
interests fall mainly in Computer Vision, deep learning, deep
reinforcement learning and robotics vision.
-
Title:
Autonomous Machine powered by Computer Vision Abstract:
Autonomous Machines (e.g. self-driving car, drone and robot arm)
keep arising as computer vision technology develops. In this talk,
how computer vision powers autonomous machine will be introduced,
including better perception, better auto-planning and better
knowledge. For better perception, some recent advanced deep learning
and 3D vision technologies will be presented. For better
auto-planning, deep reinforcement learning (including imitation
learning) will be introduced. Finally, we will revisit some recent
important knowledge-based project in computer vision, such as,
visual genome and ShapeNet to discuss how to apply visual knowledge
to improve both perception and auto-planning. Finally, we focused on
the relationship among perception, auto-planning and knowledge and
possible future directions.
|
|
-
陈仁杰,德国马克斯普朗克计算机所
https://people.mpi-inf.mpg.de/~chen/
陈仁杰,德国马克斯普朗克计算机所研究员。2005年于浙江大学获得学士学位,2010年于浙江大学获得应用数学专业博士学位。2011年至2015年于以色列理工大学和美国北卡罗来纳大学教堂山分校从事博士后研究,2015年至今工作于德国马普计算机所。研究领域为计算机图形学,主要研究方向包括几何处理和建模、计算几何及裸眼3D显示器等。近年来在SIGGRAPH,
Eurographics, SGP, TVCG等国际重要期刊及会议上发表学术论文多篇。
-
Title:
Parallel geometry processing on GPU Abstract:
It has been over a decade since the CPU industry shifted its
focus towards the multi-core architecture, however many existing and
newly developed algorithms in computer graphics and geometry
processing are still sequential in nature, which makes it difficult
to unleash the parallel computation powers of modern multi-core
CPUs. In this talk, we will discuss how to take the parallel
computing viewpoint and re-design algorithms for some geometry
processing problems. Moreover, we will talk about how to implement
algorithms on massively parallel GPUs for computationally expensive
while performance demanding applications.
|
|
|
|
|
|
-
沈小勇,香港
中文大学
http://xiaoyongshen.me/
Xiaoyong Shen got his Ph.D. degree in Computer Science and
Engineering Department in the Chinese University of Hong Kong in
2016. His supervisor is Prof. Jiaya Jia. Before that, he received
the B. S. degree in Computational Mathematics and M. S. degree in
Applied Mathematics from Zhejiang University in 2010 and 2012
respectively, under the supervision of Prof. Ligang Liu. His
research interest includes computer graphics and computer vision.
-
Title:
Awesome Applications of Deep Learning in Computer Vision Abstract:
Recently, the algorithms based on deep leaning have achieved the
state-of-the-art performance in many computer vision applications
including object detection, image classification, image
segmentation, image generation, etc. In this talk, a set of typical
and successful applications of deep learning in computer vision will
be presented. The understandings of deep learning frameworks for
different problem will be also illustrated. Lastly, I will show some
product-level deep learning solutions from our research group and
the underlying tricks will be also analyzed.
|
|
-
韩晓光,香港大学
http://i.cs.hku.hk/~xghan
韩晓光,香港大学博士在读(2013年-至今,即将毕业),2009年本科毕业于南京航空航天大学数学系,2011年于浙江大学应用数学专业获得硕士学位,并于2011年至2013年间于香港城市大学数字媒体学院任研究助理。自2009年开始,韩晓光一直从事计算机图形学,计算机视觉以及计算几何方面的研究工作,主要包括图像和视频的编辑,三维建模,本征图分解以及三维网格上的测地计算等。韩晓光目前的主要研究兴趣在基于深度学习技术的三维模型获取。他在该领域取得了一定的成果,并均发表在计算机图形学领域的重要国际期刊及会议上,包括ACM
SIGGRAPH/SIGGRAPH Asia, IEEE CG&A, Graphical Models等。
|
|
-
黄晓煌,"酷家乐”,创始人兼董事长
https://www.kujiale.com/
黄晓煌,第十三批 “国家千人计划”入选,本科毕业于浙江大学竺可桢学院,
计算机图形学方向,导师鲍虎军;获得伊利诺伊大学香槟分校(UIUC)全额奖学金,导师 Wenmei-Hwu 院士, 从事GPGPU领域研究,获得硕士学位。
在美国英伟达Nvidia担任软件工程,主要参与CUDA语言开发。其创办的酷家乐(www.kujiale.com)是以GPGPU分布式并行计算和计算机图形学为技术核心,推出的VR智能室内设计平台。于2013年11月上线,10秒生成效果图,5分钟生成装修方案。2016年,公司估值达3亿美金,团队400多人。
|
|
|
|
|
|
-
Title:
三维人脸重建及其应用 Abstract:
In recent years, face related tasks including face alignment and
face recognition have achieved great success thanks to the deep
learning. However, due to the limitations caused by the image
formation process, the 2D face recognition is still sensitive to
large view, challenging expressions and lighting conditions. On the
other hand, the face recognition system is required to be robust to
extremely challenging conditions in real applications. In this talk,
I will introduce our recent 3D assisted face analysis works
including 3D face reconstruction from image, normalization based
face recognition, and the experimental results demonstrates the
improvements over traditional 2D approaches.
|
|
-
宋鹏,中国科学技术大学
http://staff.ustc.edu.cn/~songpeng
宋鹏,中国科学技术大学特任副研究员。2007年本科毕业于哈尔滨工业大学航天学院,2009年硕士毕业
于哈尔滨工业大学深圳研究生院,2013年于新加坡南洋理工大学计算机科学与工程学院获得博士学位。
主要研究方向为计算机图形学、计算机视觉、人机交互。近年来在SIGGRAPH, SIGGRAPH Asia, TVCG,
CHI等国际重要期刊会议上发表学术论文20余篇。
|
|
-
Title:
Real Walking Mapping Computation and Its Applications in VR Abstract:
在VR应用中为了提供沉浸式的体验,将实时感渲染和real walking结合起来是一个很不错的方案。实时感渲染通过现有的HMD已经能实现,但是real
walking存在一个局限:不能在小的实际空间中去体验大的虚拟场景。为此,有很多的方法被提出,包括space manipulation,
physical prop, redirected walking and warpped
space。在本课程中,我首先会综述性地介绍这些相关技术,然后介绍warpped space方法的算法流程,最后介绍我们的基于warpped
space的且适合大场景映射的方法。
|
|
-
刘利刚,中国科学技术大学
http://staff.ustc.edu.cn/~lgliu
刘利刚,中国科学技术大学教授,博士生导师,中国科学院“百人计划”,中国科学院特聘研究员。于2001年在浙江大学获得应用数学博士学位;2001年至2004年期间在微软亚洲研究院工作;2004年至2011年期间在浙江大学数学系工作。2009年至2011年期间,在美国哈佛大学进行学术访问研究。研究兴趣包括计算机图形学,3D几何建模与处理,3D打印中的几何优化等。主持国家自然科学基金项目4项,2012年获得国家自然科学“优秀青年基金”项目。获得国家发明专利2项,计算机软件著作权15项。获得“微软青年教授”奖(2006)、陆增镛CAD&CG高科技奖一等奖(2010)、国家自然科学奖二等奖(2013)、中科大校友基金会青年教师事业奖(2014)、中国科大—兴业证券教育奖(2016)等奖项。国际会议GMP
2017大会共同主席,SPM 2014, SGP 2015, CVM 2016, CAD/Graphics
2017的论文共同主席。学术期刊IEEE TVCG, IEEE CG&A, CGF, CAGD, The Visual
Computer及《软件学报》编委。中国计算机学会计算机辅助设计与图形学专业委员会常务委员,中国工业与应用数学学会几何设计与计算专业委员会秘书长。
|
|
主办单位:中国科学技术大学
协办单位:中国图像图形学学会
|
|
历年暑期课程
|
|
Copyright © 2017 GCL , USTC |
|