This paper addresses the problem of generic object classification from three-dimensional depth or meshed data. First, surface patches are segmented on the basis of differential geometry and quadratic surface fitting. These are represented by a modified Gaussian image that includes the well-known shape index. Learning is an interactive process in which a… (More)
In spite of the rapid growth in the application of active 3D sensing technologies , it has proved difficult to acquire surface data from transparent objects due to the high transmittance and specularity of the surfaces and the confusion caused by multiple returns. In this paper, we describe how active time-of-flight range sensing using photon counting can… (More)
We present a novel method to relight video sequences given known surface shape and illumination. The method preserves fine visual details. It requires single view video frames, approximate 3D shape and standard studio illumination only, making it applicable in studio production. The technique is demonstrated for relighting video sequences of faces. Photo… (More)
The surface normals of a 3D human model, generated form multiple viewpoint capture, are refined using an iterative variant shape-from-shading technique to recover fine details of clothing. The method requires the images to consist of a number of uniformly coloured surface patches.
— We present a novel method to relight video sequences for multimedia applications given known surface shape and original illumination. The method preserves fine visual details. It requires single view video frames, approximate 3D shape and known illumination only, making it applicable for multimedia and studio production. The technique is demonstrated for… (More)