Department of Image Processing

Perceiving the environment in 3D is a fundamental property of the human visual system. While significant advances have been made in the field of computer vision during the past few years, most of the computer vision algorithms are still essentially processing the visual information in 2D space. It is highly likely that the next big thing in computer vision will be 3D perception, where conventional geometric approaches are still mainly used but machine learning based approaches are nowadays becoming more common. In this talk, I will briefly introduce our recent work on 3D computer vision including multi-view stereo, visual SLAM, and pose estimation. Also, applications to mobile vision including computational photography and augmented reality will be addressed.