Paper Info
Title
Towards Complete Free-Form Reconstruction of Complex 3D Scenes from an Unordered Set of Uncalibrated Images.
Abstract
This paper describes a method for accurate dense reconstruction of a complex scene from a small set of high-resolution unorganized still images taken by a hand-held digital camera. A fully automatic data processing pipeline is proposed. Highly discriminative features are first detected in all images. Correspondences are then found in all image pairs by wide-baseline stereo matching and used in a scene structure and camera reconstruction step that can cope with occlusion and outliers. Image pairs suitable for dense matching are automatically selected, rectified and used in dense binocular matching. The dense point cloud obtained as the union of all pairwise reconstructions is fused by local approximation using oriented geometric primitives. For texturing, every primitive is mapped on the image with the best resolution. The global structure reconstruction in the first step allows us to work with an unorganized set of images and to avoid error accumulation. By using object-centered geometric primitives we are able to preserve the flexibility of the method to describe complex free-form structures, preserve the possibility to build the dense model in an incremental way, and to retain the possibility to refine the cameras and the dense model by bundle adjustment. Results are demonstrated on partial models of a circular church and a Henri de Miller's sculpture. We observed spatial resolution in the range of centimeters on objects of about 20 m in size.
Year
DOI
Venue
2004
10.1007/978-3-540-30212-4_1
Lecture Notes in Computer Science
Keywords
Field
DocType
bundle adjustment,spatial resolution,high resolution,computer science,point cloud
Distortion (optics),Computer vision,Epipolar geometry,Bundle adjustment,Computer science,Geometric primitive,Digital camera,Artificial intelligence,Point cloud,Discriminative model,Small set
Conference
Volume
ISSN
Citations 
3247
0302-9743
9
PageRank 
References 
Authors
0.83
22
6
Name
Order
Citations
PageRank
Hugo Cornelius1452.36
Radim Sára232548.58
Daniel Martinec342020.77
Tomas Pajdla43510242.90
Ondrej Chum55677330.20
Jiri Matas628314.03