Labeling video data is an essential prerequisite for many vision applications that depend on training data, such as visual information retrieval, object recognition, and human act...
We propose to incorporate a priori geometric constraints in a 3?D stereo reconstruction scheme to cope with the many cases where image information alone is not sufficient to accur...
The notion of a virtual sensor for optimal 3D reconstruction is introduced. Instead of planar perspective images that collect many rays at a fixed viewpoint, omnivergent cameras c...
This paper presents GeoS, a new algorithm for the efficient segmentation of n-dimensional image and video data. The segmentation problem is cast as approximate energy minimization ...
We present a method for estimating intrinsic images from a fixed-viewpoint image sequence captured under changing illumination directions. Previous work on this problem reduces the...
Yasuyuki Matsushita, Stephen Lin, Sing Bing Kang, ...