Two talks for the price of one! I will present my recent work on the challenging problem of stereo matching of scenes with little or no surface texture, attacking the problem from two very different angles.
First, I will discuss how surface orientation priors can be added to the popular semi-global matching (SGM) algorithm, which significantly reduces errors on slanted weakly-textured surfaces. The orientation priors serve as a soft constraint during matching and can be derived in a variety of ways, including from low-resolution matching results and from monocular analysis and Manhattan-world assumptions.
Second, we will examine the pathological case of Mondrian Stereo -- synthetic scenes consisting solely of solid-colored planar regions, resembling paintings by Piet Mondrian. I will discuss assumptions that allow disambiguating such scenes, present a novel stereo algorithm employing symbolic reasoning about matched edge segments, and discuss how similar ideas could be utilized in robust real-world stereo algorithms for untextured environments.
Biography: Daniel Scharstein is the Charles A. Dana Professor of Computer Science at Middlebury College in Vermont. He studied Computer Science at the Universität Karlsruhe, Germany, and received his PhD from Cornell University in 1997. His research interests include computer vision, image-based rendering, robotics, and performance evaluation. He maintains the well-known Middlebury datasets and benchmarks at http://vision.middlebury.edu, for which he received the IEEE Mark Everingham Prize in 2015. He is a member of the Vermont Academy of Science and Engineering and a senior member of the IEEE.