2018-中国计算机辅助设计与图形大会与全国几何设计与计算大会特邀报告
报告题目:从数值模拟到数字孪生:关键技术与发展趋势

谭建荣院士

浙江大学

报告摘要:具体摘要信息待定

讲者简介:谭建荣,浙江湖州人,中国工程院院士,国家973项目首席科学家,浙江大学求是特聘教授,博士生导师 担任浙江大学设计工程及自动化系主任,浙江大学机器人研究院名义院长,中国大数据技术与应用产业联盟理事长,中国机械工程学会副理事长,中国图学学会副理事长,教育部工程图学教学指导委员会主任,先后获“科技部十五863先进个人”、“科技部十一五国家科技计划执行突出贡献奖”、“全国优秀科技工作者”等荣誉和称号。主要从事数据建模与虚拟现实,数字设计与智能製造方面的研究,获国家科技进步二等奖4项,省部级科技进步一等奖7项,教学成果获国家级优秀教学成果奖3项,其中一等奖1项,二等奖2项。获发明专利和软件著作登记权56项。

报告题目:计算机视觉与摄影测量的协同发展

龚健雅院士

武汉大学

报告摘要:具体摘要信息待定

讲者简介:龚健雅,博导,教授,测绘与地理信息学家,中国科学院院士,现任武汉大学遥感信息工程学院院长。1957年4月生于江西省樟树市。1982年毕业于华东地质学院测量系,1992年于武汉测绘科技大学获博士学位。2011年当选中国科学院院士。国家杰出青年基金获得者、教育部“长江学者”特聘教授、973项目首席科学家、国家自然科学基金创新群体学术带头人、国家测绘局科技领军人才、国务院第六届学科评议组测绘学科组召集人,国际摄影测量与遥感学会第六委员会主席。主要从事地理信息理论和几何遥感基础研究。多次获得国家科技进步奖。

报告题目:自然人机交互

史元春教授

清华大学

报告摘要:自然人机交互研究什么?人机交互是一个典型的学科交叉的研究领域,从计算的角度看,是面向人的性能的计算接口和过程上的优化,人的性能的可计算性发觉和交互接口与过程的优化,需要多个相关学科的研究者密切合作。交互技术已经成为终端和应用创新的核心竞争力,自然交互是发展趋势。所谓的自然,是在信息呈现和交互表达上,最大程度地符合人对现实世界已有的认知,信道充分,并能降低甚至无须学习成本,而在表达上,还体现在人不需要很精准的表达,可以是某种模糊的表达和传达的方式,而机器端能够给我们准确的理解和精准的服务。

讲者简介:史元春,清华大学计算机系"长江学者"特聘教授,她的主要研究方向为人机交互、普适计算、多媒体、网络教育技术等,近年两次获得国家科技进步奖。史元春是CCF会士,常务理事,曾任普适计算专委主任,《CCCF》副主编、专题主编,现任人机交互专委会副主任。史元春于清华大学计算机系获得学士、硕士、博士学位,1993年起在该系任教,2015年担任清华大学全球创新学院GIX院长,GIX(Global Innovation eXchange) 是清华大学在海外建立的第一个实体教研平台,与华盛顿大学合作在美国西雅图创办。史元春教授是国家重点研发计划项目“人机交互自然性的计算原理”(2016YFB1001200)的首席科学家,项目批复经费2400万。

报告题目:混合现实引导医学精准诊疗研究

杨健教授

北京理工大学

报告摘要:微创外科技术已广泛应用于颅底肿瘤、冠脉搭桥、肝癌微波消融等手术的治疗过程。目前,临床手术常规引导图像为超声、X光和内镜,其缺乏立体空间信息和皮下内部结构信息。由于手术视野狭小,导致手术难度高且风险大。混合现实技术是把虚拟生成的影像和真实的世界进行融合,实现对真实世界信息的“增强”。在军事、工业、医疗、教育等方面,混合现实技术应用广泛,并且其在医疗领域是一个重要的发展方向。结合增强现实的手术治疗方式,能够帮助医生看到病人内部组织结构。针对当前临床医学中快速发展的影像引导微诊疗,本研究团队在计算机辅助诊疗的精准导航方向围绕核心问题进行了深入研究,发展了增强现实手术导航理论,提出了低对比度医学图像重建、器官血管精确分割、多模态图像弹性配准和融合显示方法,结合增强现实可视化理论体系,成功研制了基于混合现实技术的鼻内镜手术导航系统、心血管介入导航系统和肝肿瘤微创治疗系统。

讲者简介:杨健,博士,教授,博士生导师。2000、2007年分别获北京理工大学光电子学专业学士学位和光学工程专业博士学位。2007年4月至2009年4月期间在加拿大皇家科学院院士、多伦多大学R. Mark Henkelman教授指导下从事博士后研究工作。长期从事虚拟现实与增强现实、医学图像处理和手术导航等方面的研究工作,十三五重点研发计划项目首席科学家。在IEEE T-MI、IEEE T-IP、IEEE T-BME、IEEE T-VCG等国际著名期刊上发表SCI期刊论文79篇(第一作者和通讯作者论文45篇)。作为第一发明人申报国家发明专利60余项,授权24项。研究成果获2014年度教育部技术发明奖一等奖,获2017年度国家技术发明二等奖。

报告题目:Adding Rotation into 3D Printing

Prof. Charlie Wang

Delft University of Technology

报告摘要:Called 3D printing, the process of Additive manufacturing (AM) in most commercial systems is however taken in a 2.5D manner – materials are accumulated layer upon layer in planes along a fixed printing direction. Overhanging regions are generally fabricated by inserting supporting structures, which are difficult to remove. This talk covers the techniques recently developed for overcoming this challenge by adding rotation into 3D printing. First of all, motivated by a work of orientation-driven shape optimizer attempting to slim down the need of support, rotations have been introduced to handle overhangs. Secondly, the method for determining an optimal printing direction is introduced. Our framework for computing an optimized 3D printing direction is formulated as a combination of metrics including area of support, visual saliency, preferred viewpoint and smoothness preservation. A training-and-learning methodology is developed to obtain a closed-form solution for our perceptual model. A solid decomposition based approach is applied to segment a model into sub-regions that are printed along different (but fixed) directions in a support-free way. Lastly, a more advanced hardware with continuous multi-axis motions (e.g., a robotic arm) can be utilized for 3D printing along more complicated tool-paths – i.e., a real 3D printing process. Automatic tool-path planning for multi-axis 3D printing is based on two successive decompositions, first volume-to-surfaces and then surfaces-to-curves. Details of this technique and its potential in a variety of applications will be presented at the end of this talk.

讲者简介:Charlie C.L. Wang is currently a Professor and Chair of Advanced Manufacturing in the Department of Design Engineering at Delft University of Technology, The Netherlands. Prior to this position, he was a Full Professor / Associate Professor / Assistant Professor of Mechanical and Automation Engineering at the Chinese University of Hong Kong (CUHK), where he started his academic career in 2003. He received his Ph.D. (2002) degrees in mechanical engineering from Hong Kong University of Science and Technology (HKUST). Prof. Wang received a few awards from professional societies including the ASME CIE Excellence in Research Award (2016), the ASME CIE Young Engineer Award (2009), the Best Paper Awards of ASME CIE Conferences (twice in 2008 and 2001 respectively), the Prakash Krishnaswami CAPPD Best Paper Award of ASME CIE Conference (2011), and the NAMRI/SME Outstanding Paper Award (2013). He serves on the editorial board of a few journals, including Computer-Aided Design, IEEE Transactions on Automation Science and Engineering, and ASME Journal of Computing and Information Science in Engineering. He is a Fellow of American Society of Mechanical Engineers (ASME). His current research interests span geometric computing, computational design, advanced manufacturing, and robotics.

报告题目:BA-Net: Dense Bundle Adjustment Network

谭平教授

西蒙弗雷泽大学

报告摘要:This work introduces a nueral network to solve the structure-from-motion (SfM) problem via feature bundle adjustment (BA), which explicitly enforces multi-view geometry constraints in the form of feature reprojection error. The whole pipeline is differentiable, so that the network can learn suitable feature representations that make the BA problem more trackable. Furthermore, this work introduces a novel depth parameterization to recover dense per-pixel depth. The network first generates some bases depth maps according to the input image, and optimizes the final depth as a linear combination of these bases via feature BA. The bases depth map generator is also learned via end-to-end training. The whole system nicely combines domain knowledge (i.e. hard-coded multi-view geometry constraints) and machine learning (i.e. feature learning and basis depth map generator learning) to address the challenging SfM problem. Experiments on large scale real data prove the success of the proposed method.

讲者简介:Ping Tan is an associate professor at the School of Computing Science in the Simon Fraser University (SFU). Before that, he was an associate professor at the Department of Electrical and Computer Engineering in the National University of Singapore (NUS). From 2016 to 2018 April, he worked in Qihoo 360's AI Lab in Beijing, China as the Deputy Director. He has served as an editorial board member of the International Journal of Computer Vision (IJCV), Computer Graphics Forum (CGF), and the Machine Vision and Applications (MVA). He has served as an area chair of CVPR and a program committee member of SIGGRAPH, SIGGRAPH Asia.