Single view reconstruction approaches infer the structure of 3D objects or scenes from 2D
images. This is an inherently ill-posed problem. An abundance of reconstruction approaches …

We propose a novel algorithmic solution for estimating a three-dimensional model of an
object observed in a single image. Based on a minimal user input, the algorithm interactively …

We propose a method for simultaneous shape-constrained segmentation and parameter
recovery. The parameters can describe anything from 3D shape to 3D pose and we place no …

In this paper we extend our previous work and consider two related problems: the first one
proposes a method for the scheduling of static sensors in a network where it is assumed that …

While recent deep neural networks have achieved promising results for 3D reconstruction
from a single-view image, these rely on the availability of RGB textures in images and extra …

This thesis investigates two special cases of 3D reconstruction: The reconstruction from only
a single input image and the reconstruction over time from multiple-view image sequences …

Reconstructing the 3D geometry from a single image is a strongly ill-posed problem and
unique depth values can only be inferred in very specific cases. In this thesis several …

We propose a method for simultaneous shape-constrained segmentation and parameter
recovery. The parameters can describe anything from 3D shape to 3D pose and we place no …