3D Scene Reconstruction by Stereo Methods for Analysis and Visualization of Sports Scenes

摘要

The 3D reconstruction of image and video scenes by stereo analysis is an important topic in computer vision research. In this talk, we first present some principles of stereo algorithms and recent developments. We then demonstrate two applications of stereo reconstruction for the analysis and visualization of human movement: (a) We employ depth maps derived from sport scenes for novel view synthesis, and (b) we show how stereo processing can be used for expressive visualization of human motion in a comic-like style.