While the majority of today’s object class models provide only 2D bounding boxes, far richer output hypotheses are desirable including viewpoint, fine-grained category, and 3D geometry estimate. However, models trained to provide richer output require larger amounts of training data, preferably well covering the relevant aspects such as viewpoint and fine-grained categories. In this paper, we a...

We present an interactive player for free-viewpoint video. Free-viewpoint video data typically consist of large amounts of video datasets captured from multiple cameras and additional inter-view and frame information. Neither the size nor the representation of this data is appropriate for real-time rendering. Inspired by a new image interpolation approach based on correspondence fields, we prop...

We propose a method that can reconstruct both a 3D facial shape and camera poses from freehand multi-viewpoint snapshots. This method is based on Active Shape Model (ASM) using a facial shape database. Most ASM methods require an image in which the camera pose is known, but our method does not require this information. First, we choose an initial shape by selecting the model from the database w...

The paper presents a new coding technique for images taken from arbitrary recording positions around a static scene, based on reconstructed object geometry. Such data structures occur in image-based rendering applications where many hundreds to thousands of images need to be stored and transmitted. Approximate scene geometry enables disparity compensation as well as occlusion detection, leading...

This paper discusses semantic technologies for multi-perspective issues of ontologies based on ontological viewpoint management. We developed two technologies and implement them in environmental and medical domain. The first one is conceptual map generation tool which allows the users to explore an ontology according to their own perspectives and visualizes them in a user-friendly form, i.e. co...

Different stakeholders in the design of an enterprise information system have their own view on that design. To help produce a coherent design this paper presents a framework that aids in specifying relations between such views. To help produce a consistent design the framework also aids in specifying consistency rules that apply to the view relations and in checking the consistency according t...

Abstract: A multi-viewpoint integration scheme is introduced to recognize scene features prior to physical access. In this schematics, chromatic complexity of vehicle’sand bird’s-eye-views of roadway scenes are matched to extend GPS tracks towards possible destinations. Saliency patterns arising in destination images are anticipatively extracted to control the focus of inherent and machine visi...

The reference model of Open Distributed Processing (ODP) prescribes the use of a number of viewpoints (i.e. partial specifications). Specifications written in these viewpoints are likely to use different notations, e.g. the Computational Viewpoint is likely to include descriptions given in CORBA IDL, whilst the Information Viewpoint might well use a schemabased notation such as Z. To support su...

In two experiments, two forms of interactivity were investigated concerning their effect on presence: (1) the possibility of viewpoint changes, and the (2) interaction with other characters in the virtual environment. A multi-component presence measure was used as dependent variable. The results show that viewpoint changes enhance spatial presence and experienced realism. The presence of other ...