*This talk is cancelled, to be rescheduled at a later date.
Speaker: Qixing ‘Peter’ Huang, Toyata Technical Institute in Chicago
Title: Visual Computing Using Big 3D Data
Over the past decade, the quantity of accessible visual data has undergone unprecedented expansion. This data is not only vast but also exists within numerous modalities such as images, videos, and 3D models. While researchers have aptly exploited the inflation of these first two areas, the significant growth in 3D data has been predominantly overlooked. In this talk, I will present algorithms that utilize big 3D data to accomplish many previously hard or even impossible tasks in visual computing. These include reconstructing complete 3D models from single images, identifying meaningful correspondences between drastically different objects (e.g., between an elephant and a cat) as well as extracting semantic parts of an object without supervision. The guiding principle is to establish high-quality maps for aggregating and propagating information. I will discuss fundamental map computation tools for large-scale datasets.
Qixing ‘Peter’ Huang is currently a research assistant professor at the Toyata Technical Institute in Chicago. He obtained his PhD in Computer Science from Stanford University and his MS and BS in Computer Science from Tsinghua University. He has also worked at Adobe Research and Google Research, where he developed some of the key technologies for Google Street View. Dr. Huang’s research spans the fields of computer vision, computer graphics, and machine learning. In particular, he is interested in designing new algorithms that process and analyze big geometric data (e.g., 3D shapes/scenes). 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. Qixing has published extensively at SIGGRAPH, CVPR and ICCV, and has received grants from NSF and various industry gifts. He also received the best paper award at the Symposium on Geometry Processing 2013.