|search externally:||Google Scholar, Springer, CiteSeer, Microsoft Academic Search, Scirus , DBlife|
I am currently a 5th year PhD student in the computer vision group at LEMS lab, Brown University. My research interests include multi-view stereo (or inverse ray tracing in my words) and scene understanding (or scene graph parsing), using statistical methods including Markov random fields, statistical learning and inference, and optimization. Philosophically, I take computer vision as an inverse problem, and I tackle all the problems in this perspective. And from my experience, this approach seems very general and promising. For example, the 3D reconstruction problem is taken as an inverse problem of image rendering. Along this philosophical direction, we have developed the inverse ray tracing technique to reconstruct the 3D scenes (and also the background) from multiple images. Similarly, we take the image understanding problem as inversing the scene graph composition problem, that is, the scene graph parsing problem. Take a look at the research page for more details.
Besides research, at Brown I have learned a lot in different subjects, including pure math, applied math, computer science, engineering and etc. As a personal log, I maintained a list of the classes I have taken at Brown, which you may find useful.
I am going to finish my PhD in the summer of 2010. I am looking for a research position in the area of computer vision and machine learning.
as author at 23rd IEEE Conference on Computer Vision and Pattern Recognition 2010 - San Francisco,
together with: Yasutaka Furukawa, Dirk Schnieders, Carl Olsson, Qingxiong Yang, Xiaoyan Hu, Yekeun Jeong, Tai-Pang Wu, Yuping Lin, Richard Newcombe, Tali Bahsa, Vivek Pradeep, Junghyun Kwon, Ricardo Fabbri, Margarita Chli, Peter Lindstrom, Branislav Micusik, Michael Bleyer, Guillaume Batog, Arjun Jain, Michela Farenzena, Jun Sato,