Event Location: NSH 1507
Bio: Yuandong Tian is currently a second-year Ph.D candidate in Robotics,
Carnegie Mellon University. His research interest is computer vision and
machine learning. He is now working on image distortion estimation and
non-rigid motion capture alignment with his advisor Srinivasa
Narasimhan. He received his Bachelor and Master degree in Computer
Science from Shanghai Jiao Tong University in 2005 and 2008 respectively.

Abstract: A video sequence of an underwater scene taken from above the water
surface suffers from severe distortions due to water fluctuations. In this
paper, we simultaneously estimate the shape of the water surface and
recover the planar underwater scene without using any calibration
patterns, image priors, multiple viewpoints or active illumination. The
key idea is to build a compact spatial distortion model of the water
surface using the wave equation. Based on this model, we present a novel
tracking technique that is designed specifically for water surfaces and
addresses two unique challenges—the absence of an object model or
template and the presence of complex appearance changes in the scene due
to water fluctuation. We show the effectiveness of our approach on both
simulated and real scenes, with text and texture.