GAMES Webinar 2019 – 106期 (SIGGRAPH 2019 专题（海外）)|臧光明(King Abdullah University of Science and Technology)，黄其兴（德克萨斯大学奥斯汀分校）
【GAMES Webinar 2019-106期】
报告题目：Tensor Maps for Synchronizing Heterogeneous Shape Collections
Establishing high-quality correspondence maps between geometric shapes has been shown to be the fundamental problem in managing geometric shape collections. Prior work has focused on computing efficient maps between pairs of shapes, and has shown a quantifiable benefit of joint map synchronization, where a collection of shapes are used to improve (denoise) the pairwise maps for consistency and correctness. However, these existing map synchronization techniques place very strong assumptions on the input shapes collection such as all the input shapes fall into the same category and/or the majority of the input pairwise maps are correct. In this paper, we present a multiple map synchronization approach that takes a heterogeneous shape collection as input and simultaneously outputs consistent dense pairwise shape maps. We achieve our goal by using a novel tensorbased representation for map synchronization, which is efficient and robust than all prior matrix-based representations. We demonstrate the usefulness of this approach across a wide range of geometric shape datasets and the applications in shape clustering and shape co-segmentation.
Qixing Huang is an assistant professor of Computer Science at the University of Texas at Austin. He obtained his PhD in Computer Science from Stanford University. He was a research assistant professor at Toyota Technological Institute at Chicago before joining UT Austin. Dr. Huang’s research spans the fields of computer vision, computer graphics, and machine learning, and publishes extensively in venues such as SIGGRAPH, CVPR, ICCV, ECCV, NeuriPS, ICML, and etc. In particular, his recent focus is on developing machine learning algorithms (particularly deep learning) that leverage Big Data to solve core problems in computer vision, computer graphics and computational biology. He is also interested in statistical data analysis, compressive sensing, low-rank matrix recovery, and large-scale optimization, which provides theoretical foundation for his research. He also received the best paper award at the Symposium on Geometry Processing 2013, the best dataset award at the Symposium on Geometry Processing 2018, and the most cited paper award of Computer-Aided Geometric Design in 2010 and 2011. Dr. Huang was an area chair for CVPR 2019 and ICCV 2019. He will serve as a paper co-chair of Symposium on Geometry Processing 2020 and an advisory board member of Eurographics 2020.
报告嘉宾：臧光明，King Abdullah University of Science and Technology
报告题目：Warp-and-Project Tomography for Rapidly Deforming Objects
During the last years, many methods were proposed for the capture and the reconstruction of dynamic 3D scenes, using visible light scanning. However, such methods cannot reproduce internal structures, or deal with the occlusions in the scanned objects. In our work, a warp-and-project tomography was introduced to reconstruct dynamic objects with internal structures like wilting rose and growing seeds. In this talk, I will show several applications of inverse problems in graphics and imaging. Through a combination of a new image acquisition strategy, a space-time image formation model, and an alternating, multi-scale solver for image reconstruction and motion estimation, we achieve several general approaches that can be used to analyze a wide range of dynamic phenomena.
Guangming Zang is a graduating Ph.D. candidate in Computer Science at the Visual Computing Center (VCC) of King Abdullah University of Science and Technology (KAUST) under the supervision of Prof. Wolfgang Heidrich and Prof. Peter Wonka. His research interests lie in the area of computational imaging, computer graphics, optimization and machine learning. He is currently working on the intersection between data-driven and model-driven methods.
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；