Many computer vision algorithms limit their performance by ignoring the underlying 3D geometric structure in the image. We show that we can estimate the coarse geometric propertie...
Abstract In this paper we extend a multi-camera model for simultaneous estimation of 3d position, normals, and 3d motion of surface patches [17] to be able to handle brightness cha...
In this paper, we address the problem of 3D volume reconstruction from depth adjacent subvolumes (i.e., sets of image frames) acquired using a confocal laser scanning microscope (...
Recently, various technologies have become available for scanning real-world objects, enabling rapid and accurate shape acquisition. In most cases, such solutions have high cost, ...
We present 3D video fragments, a dynamic point sample framework for real-time free-viewpoint video. By generalizing 2D video pixels towards 3D irregular point samples we combine t...