GAMES Webinar 2020 – 130期(几何处理专题) |Zhiqin Chen(Simon Fraser University, Canada),Peng Song(Singapore University of Technology and Design)
【GAMES Webinar 2020-130期】（几何处理专题）
报告嘉宾1：Zhiqin Chen, Simon Fraser University, Canada
报告题目：Learning Implicit Representations for Shape Generation and Analysis
A key problem for generating shapes from neural networks is how to represent the shapes. Many representations (point clouds, voxels, deformable meshes, etc) have been adopted for generative models and achieved great success. However, generating shapes with high visual quality remains a challenge. In this talk, I will describe how implicit field representation can be incorporated with deep neural networks for shape generation and analysis. Furthermore, I will show our latest advancement — an interpretable version of the network, where we can extract explicit meshes from the parameters, in contrast to obtaining the iso-surfaces via marching cubes.
Zhiqin Chen is a first-year Ph.D. student at Simon Fraser University, under the supervision of Prof. Hao (Richard) Zhang. His research interest is Computer Graphics with specialty in Geometric Modeling and Machine Learning. He received his Master’s degree from Simon Fraser University in 2019, and Bachelor’s degree from Shanghai Jiao Tong University in 2017.
报告嘉宾2：Peng Song, Singapore University of Technology and Design
报告题目：3D Interlocking Assemblies: Design and Applications
3D assemblies refer to objects that combine multiple component parts into a structure with a specific form and/or functionality.Rather than relying on additional fasteners such as nails and screws to connect the parts, component parts can be interlocked into a steady assembly based on their own geometric arrangements. This talk revisits the notion of 3D interlocking, and explores the governing mechanics of general 3D interlocking assemblies. From this, constructive approaches are developed for computational design of various new interlocking assemblies such as puzzles, furniture, 3D printed objects, and architecture. These interlocking assemblies are ready for fabrication and their steadiness have been validated in our experiments.
Peng Song is an Assistant Professor at the Pillar of Information Systems Technology and Design, Singapore University of Technology and Design (SUTD) since 2019. Prior to joining SUTD, Peng was a research scientist at EPFL, Switzerland, an associate researcher at University of Science and Technology of China, and a research fellow at Nanyang Technological University, Singapore. He received his PhD from Nanyang Technological University, Singapore in 2013, his master’s and bachelor’s degrees both from Harbin Institute of Technology, China in 2010 and 2007 respectively. His research interests lie in computer graphics, with a focus on the modeling, processing, design and fabrication of digital 3D geometry.
GAMES主页的“使用教程”中有 “如何观看GAMES Webinar直播？”及“如何加入GAMES微信群？”的信息；