Low-cost model reconstruction from image sequences

Authors:
Caleb Lyness;Otto-Carl Marte;Bryan Wong;Patrick Marais
Affiliations:
Collaborative Visual Computing Laboratory, University of Cape Town;Collaborative Visual Computing Laboratory, University of Cape Town;Collaborative Visual Computing Laboratory, University of Cape Town;Collaborative Visual Computing Laboratory, University of Cape Town
Venue:
AFRIGRAPH '01 Proceedings of the 1st international conference on Computer graphics, virtual reality and visualisation
Year:
2001

Citing 10
Cited 1

Marching cubes: A high resolution 3D surface construction algorithm

SIGGRAPH '87 Proceedings of the 14th annual conference on Computer graphics and interactive techniques
A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses

Radiometry
How Far 3D Shapes Can Be Understood from 2D Silhouettes

IEEE Transactions on Pattern Analysis and Machine Intelligence
A signal processing approach to fair surface design

SIGGRAPH '95 Proceedings of the 22nd annual conference on Computer graphics and interactive techniques
The digital Michelangelo project: 3D scanning of large statues

Proceedings of the 27th annual conference on Computer graphics and interactive techniques
Silhouette clipping

Proceedings of the 27th annual conference on Computer graphics and interactive techniques
Multiresolution Textures from Image Sequences

IEEE Computer Graphics and Applications
Automatic reconstruction of 3D objects using a mobile monoscopic camera

NRC '97 Proceedings of the International Conference on Recent Advances in 3-D Digital Imaging and Modeling
Texture Synthesis by Non-Parametric Sampling

ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Self-Calibration and Metric Reconstruction in spite of Varying and Unknown Internal Camera Parameters

ICCV '98 Proceedings of the Sixth International Conference on Computer Vision

3D reconstruction of a human face with monocular camera based on head movement

VIP '05 Proceedings of the Pan-Sydney area workshop on Visual information processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

A system that constructs a three dimensional model using two dimensional images taken from multiple view-points is presented. This system improves upon existing work by including several optimisations and extensions to cater for poor lighting. This system was developed with the modeling of African artworks in mind. As these artifacts are often located in remote areas, our system has to be robust enough to deal with less than ideal lighting conditions.The images used as input are obtained by filming an object, which is being rotated on a turntable. The modeling process begins with the extraction of "silhouettes" from the input images. These silhouettes are used in conjunction with the camera model to construct a volumetric representation. Following this, a surface model, consisting of a triangular mesh, is created. Finally, the surface model is texture mapped.