Abstract:
Deep learning has flooded almost every corner of computer vision/graphics. However, when talking about the important task of establishing dense correspondences across images/shapes (particularly between different instances), the impact of deep learning remains limited. In this context, the major technical challenges are 1) to handle partial similarity and geometric/topological variability, and 2) to obtain sufficient training data, as it is hard to label dense correspondence one-by-one. In this talk, I will discuss recent works that use convolutional neural networks to address these challenges.

Biography:
Qixing 'Peter' Huang is currently a research assistant professor at the Toyota 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.

Host:
Dr. Xiaoming Liu