Seminar by Konrad Schindler on September 30 (Tuesday) at 11am
Title:Piecewise rigid 3D scene flow
Abstract: I will present recent work on dense 3D scene flow estimation from stereo video
of dynamic environments. The proposed method estimates the depth and 3D motion
field of a dynamic scene from multiple consecutive frames in a sliding temporal
window, such that the estimate is consistent across both viewpoints of all
frames within the window. The observed scene is modelled as a collection of
planar patches that are consistent across views, each undergoing a rigid motion
that is approximately constant over time. Finding the patches and their motions
is cast as minimisation of an energy function over the continuous plane and
motion parameters and the discrete pixel-to-plane assignment. Our method
currently achieves leading performance on the KITTI benchmark, for both flow and
stereo computation.
