GAMES Webinar 2017-08期(Siggraph 2017论文报告)| 蒋才桂(德国Max Planck Institute for Informatics),谈建超(美国乔治梅森大学)
【GAMES Webinar 2017-08期(Siggraph 2017论文报告)】
报告嘉宾1:蒋才桂,德国Max Planck Institute for Informatics
报告时间:2017年8月10日(星期四)晚20:00-20:45(北京时间)
主持人:刘洋,微软亚洲研究院(个人主页:http://xueyuhanlang.github.io/)
论文题目:Design and Volume Optimization of Space Structures
论文信息:
蒋才桂(KAUST & MPII), 唐承成(KAUST & Stanford), Hans-Peter Seidel(MPII), Peter Wonka(KAUST). Design and Volume Optimization of Space Structures. Siggraph 2017.
报告摘要:
We study the design and optimization of statically sound and materially efficient space structures constructed by connected beams. We propose a systematic computational framework for the design of space structures that incorporates static soundness, approximation of reference surfaces, boundary alignment, and geometric regularity. To tackle this challenging problem, we first jointly optimize node positions and connectivity through a nonlinear continuous optimization algorithm. Next, with fixed nodes and connectivity, we formulate the assignment of beam cross sections as a mixed-integer programming problem with a bilinear objective function and quadratic constraints. We solve this problem with a novel and practical alternating direction method based on linear programming relaxation. The capability and efficiency of the algorithms and the computational framework are validated by a variety of examples and comparisons.
讲者简介:
Caigui Jiang is a postdoc researcher at the Max Planck Institute for Informatics. Before that, he was a Ph.D. student in Visual Computing Center (VCC) at King Abdullah University of Science and Technology (KAUST) in Saudi Arabia, under the supervision of Prof. Dr. Helmut Pottmann and Prof. Dr. Peter Wonka. He received his B.S. and M.S. degrees from Xi’an Jiaotong University (XJTU) in 2008 and 2011 respectively. His research interests are in geometric modeling, geometry processing, architectural geometry, computer graphics, and vision. Homepage: http://people.mpi-inf.mpg.de/~cjiang
报告嘉宾2:谈建超,美国乔治梅森大学
报告时间:2017年8月10日(星期四)晚20:45-21:30(北京时间)
主持人:刘洋,微软亚洲研究院(个人主页:http://xueyuhanlang.github.io/)
论文题目:基于RGB空间几何特性的图像图层分解(Decomposing Images into Layers via RGB-space Geometry)
论文信息:
Jianchao Tan, Jyh-Ming Lien,, Yotam Gingold (George Mason University). Decomposing Images into Layers via RGB-space Geometry. ACM Transactions on Graphics, 2016. (Presented at Siggraph 2017)
报告摘要:
数字图像编辑软件常常运用一种叫做图层的数据结构来创建,编辑和组织图像。然而,图层通常没有在最终的图像中显性表达,并且可能永远不会存在于扫描的绘画或拍摄的照片中。我们提出一种方法将单幅图像分解成一些图层,从而使用户更方便编辑图像。我们的分解是基于图像的RGB空间的几何特性。在RGB空间中,迭代使用线性的 Alpha 颜色混合会导致颜色点云结构始终呈现凸结构。图像点云凸包的顶点对应于调色板中的各个颜色,这些颜色也有可能是不直接存在于图像像素中的, 我们的方法能够成功找到这些调色板颜色。在提取图层的过程中,用户可以选择调色板大小(通过简化凸包的复杂度)以及选择调色板颜色(凸包的顶点)的层次顺序。然后我们解决一个优化问题提取半透明图层。使用这些图层,我们可以非常容易地给图像全局或局部地变色,以及给图像插入新图层。我们的图层表达还可以转化为一种稀疏且光滑的广义重心坐标表达。
讲者简介:
乔治梅森大学计算机系第四年博士生,导师为 Dr.Yotam Gingold. 2013年从中国科学技术大学电子工程与信息科学系本科毕业。研究兴趣为图像处理,目前具体方向为基于图层分解的图像编辑。个人主页:https://cs.gmu.edu/~jtan8
直播链接:http://webinar.games-cn.org