Face recognition and many medical imaging applications require the computation of dense correspondence vector fields that match one surface with another. In brain imaging, surfac...
Conventional photometric stereo recovers one normal direction per pixel of the input image. This fundamentally limits the scale of recovered geometry to the resolution of the input...
Abstract-- A main difficulty that arises in the context of probabilistic localization is the design of an appropriate observation model, i.e., determining the likelihood of a senso...
Maren Bennewitz, Cyrill Stachniss, Sven Behnke, Wo...
This paper addresses the problem of reconstructing surface models of indoor scenes from sparse 3D scene structure captured from N camera views. Sparse 3D measurements of real scen...
Anastasios Manessis, Adrian Hilton, Philip F. McLa...
In this paper we address the problem of simultaneous estimation of structure and restoration of images from blurred photometric measurements. Given the blurred observations of a s...