We present a method for shape reconstruction from several images of a moving object. The reconstruction is dense (up to image resolution). The method assumes that the motion is kn...
We propose a new robust focal length estimation method in multi-view structure from motion from unordered data sets, e.g. downloaded from the Flickr database, where jpeg-exif heade...
Action recognition is an important and challenging topic in computer vision, with many important applications including video surveillance, automated cinematography and understand...
We introduce an iterative algorithm for shape reconstruction from multiple images of a moving (Lambertian) object illuminated by distant (and possibly time varying) lighting. Star...
Jongwoo Lim, Jeffrey Ho, Ming-Hsuan Yang, David J....
Most existing structure from motion (SFM) approaches for unordered images cannot handle multiple instances of the same structure in the scene. When image pairs containing differen...
Richard Roberts, Sudipta Sinha, Richard Szeliski, ...