Multi Viewpoint Stereo from Uncalibrated Video Sequences

  title={Multi Viewpoint Stereo from Uncalibrated Video Sequences},
  author={Reinhard Koch and Marc Pollefeys and Luc Van Gool},
  booktitle={European Conference on Computer Vision},
This contribution describes an automatic 3D surface modeling system that extracts dense metric 3D surfaces from an uncalibrated video sequence. A static 3D scene is observed from multiple viewpoints by freely moving a video camera around the object. No restrictions on camera movement and internal camera parameters like zoom are imposed, as the camera pose and intrinsic parameters are calibrated from the sequence. 

Hand-held acquisition of 3D models with a video camera

An approach is described which achieves this goal by combining state-of-the-art algorithms for uncalibrated projective reconstruction, self-calibration and dense correspondence matching.


This contribution gives an overview of automatic 3D scene reconstruction and visualisation from uncalibrated and handheld camera image sequences. We address specifically the problems that are

Robust Calibration and 3D Geometric Modeling From Large Collections of Uncalibrated Images

This contribution focuses on calibration and 3D surface modeling from uncalibrated images, which are collected with a hand-held camera by simply waving the camera around the objects to be modeled.

Realistic 3-D scene modeling from uncalibrated image sequences

The generation of realistic 3D models for a virtual exhibition of the archaeological excavation site in Sagalassos, Turkey will be demonstrated, as the approach operates independently of object scale and requires only a single low-cost consumer photo or video camera.

Metric 3D Surface Reconstruction from Uncalibrated Image Sequences

An approach is described which achieves this goal by combining state-of-the-art algorithms for uncalibrated projective reconstruction, self-calibration and dense correspondence matching.

From image sequences to 3 D models

An approach is presented that obtains virtual models from sequences of images acquired with a hand held camera and a flexible multi-view stereo matching scheme is used to obtain a dense estimation of the surface geometry.

Reconstruction and Rendering from Image Sequences

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


A complete system that takes a video sequence of a static scene as input and generates visual 3D model that integrates state-of-the-art algorithms developed in computer vision, computer graphics and photogrammetry is presented.


An approach is described which achieves this goal by combining state-of-the-art algorithms for uncalibrated projective reconstruction, self-calibration and dense correspondence matching.

Multi-view 3D estimation and applications to match move

The paper presents a number of examples of different camera motions to highlight the versatility of 3D estimation and automatic Euclidean pose estimation in extended sequences even when views of the scene rapidly change.



3D Model Acquisition from Extended Image Sequences

A method for matching image primitives through a sequence is described, for the purpose of acquiring 3D geometric models. The method includes a novel robust estimator of the trifocal tensor, based on

Estimation of Relative Camera Positions for Uncalibrated Cameras

A non-iterative algorithm is given for determining the focal lengths of the two cameras, as well as their relative placement, assuming all other internal camera parameters to be known.

Three-dimensional computer vision: a geometric viewpoint

Results from constrained optimization some results from algebraic geometry differential geometry are shown.

Euclidean 3D Reconstruction from Image Sequences with Variable Focal Lenghts

A reconstruction method that allows to vary the focal length and is resistant to noise, and in which case also reconstruction from a moving rig becomes possible even for pure translation.

3-D Modeling of Human Heads from Stereoscopic Image Sequences

  • R. Koch
  • Computer Science
  • 1996
A passive 3-D scanning system is described that automatically computes a complete3-D surface model of a human head and shoulder part from a stereoscopic image sequence of a person rotating freely in front of the camera.

Surface segmentation and modeling of 3D polygonal objects from stereoscopic image pairs

  • R. Koch
  • Computer Science
    Proceedings of 13th International Conference on Pattern Recognition
  • 1996
An approach to automatically generate 3D polygonal models from stereoscopic image pairs of piecewise planar objects is presented. Dense disparity maps are computed by constrained epipolar block

Self-Calibration from the Absolute Conic on the Plane at Infinity

A new method to obtain a metric reconstruction from images the cameras have to be calibrated which is closely related to some of the existing methods and shows some clear advantages.

Self-calibration and metric reconstruction in spite of varying and unknown internal camera parameters

A self-calibration method is presented which efficiently deals with all kinds of constraints on the internal camera parameters and a practical method is proposed which can retrieve metric reconstruction from image sequences obtained with uncalibrated zooming/focusing cameras.

What can be seen in three dimensions with an uncalibrated stereo rig

This paper addresses the problem of determining the kind of three- dimensional reconstructions that can be obtained from a binocular stereo rig for which no three-dimensional metric calibration data is available, and shows that even in this case some very rich non-metric reconstructions of the environment can nonetheless be obtained.