Given an accurate 3-D shape model of a scene, the motion parameters of a moving camera can be recovered with high accuracy using model-based motion estimation techniques. Shape errors, however, reduce the accuracy of this kind of motion estimation considerably. In this paper, model-based motion estimation is combined with simultaneous object shape refinement. A deformable 3-D shape model of low...

Obtaining a foreground silhouette across multiple views is one of the fundamental steps in 3D reconstruction. In this paper we present a novel video segmentation approach, to obtain a foreground silhouette, for scenes captured by a wide-baseline camera rig given a sparse manual interaction in a single view. The algorithm is based on trimap propagation, a framework used in video matting. Bayesia...

The classic perspective projection is mostly used when calibrating a camera. Although this approach is fairly developed and often suitable, it is not necessarily adequate to model any camera system like fish-eyes or catadioptrics. The perspective projection is not applicable when field of views reach 180° and beyond. In this case an appropriate model for a particular non perspective camera has ...

Non-central (X-slits) images can be used in image based rendering (IBR) for new view synthesis for a viewer moving in a restricted region. Novel, i.e. previously unseen, views are rendered from virtual camera positions from a set of images captured at some predefined camera positions. The novel views correspond to camera positions not contained in the input image set. For instance, the input se...

The appearance of individuals captured by multiple non-overlapping cameras varies greatly due to pose and illumination changes between camera views. In this paper we address the problem of dealing with illumination changes in order to recover matching of individuals appearing at different camera sites. This task is challenging as accurately mapping colour changes between views requires an exhau...

This paper presents a multi-camera system to track multiple persons in complex, dynamic environments. Position measurements are obtained by carving out the space defined by foreground regions in the overlapping camera views and projecting these onto blobs on the ground plane. Person appearance is described in terms of the colour histograms in the various camera views of three vertical body regi...

This paper addresses the problem of new view synthesis from views of a scene taken from an uncalibrated translating camera. A method for synthesis of novel views which handles occlusions is proposed and a characterisation of the viewpoints for which novel views can be synthesized using the proposed scheme is given. The proposed scheme can also be used to detect translational pan in video sequen...

This contribution describes a system for 3D surface reconstruction and novel view synthesis from image streams of an unknown but static scene. The system operates fully automatic and estimates camera pose and 3D scene geometry using Structure-from-Motion and dense multi-camera stereo reconstruction. From these estimates, novel views of the scene can be rendered at interactive rates.

This paper presents a view synthesis algorithm to generate intermediate views that allows moving a virtual camera along a 1-D path. Instead of relying on accurate depth maps, the proposed method uses a disparity map that provides a dense pixel correspondence. The algorithm is able to generate images of complex real scenes that are ready to be displayed on an autostereoscopic device. Experiments...

In this paper the GPU implementation of a real-time isosurface volume-rendering system is described in detail, which aims at autostereoscopic displays. Since autostereoscopic displays provide images for many views, and thus require different camera settings in each pixel, and even in the three color channels of a pixel, naive rendering approaches would slow down the rendering process by a facto...