Paper Info
Title
Enhanced Surface Reconstruction from Wide Baseline Images
Abstract
This paper deals with the problem of dense matching from stereo images under wide baseline conditions. By considering the characteristic properties of widely separated views, we propose an extension to a recently published algorithm for detailed reconstruction of continuous surfaces. The algorithm compensates for the occurrent affine distortion between the views to allow low level intensity based comparison necessary for dense matching. The matching itself is performed by an enhanced region rowing based affine propagation method that takes surface distortion into account to handle complex piecewise-smooth surfaces. It is experimentally shown that this new method can achieve smooth and accurate reconstruction from wide baseline images of both indoor and outdoor scenes. To quantify the reconstruction results we have created realistic synthetic datasets with ground truth. These datasets form the core of a future testbed for comparison of different wide baseline surface reconstruction techniques. In the current study, results on the synthetic images are compared to the ground truth to measure the accuracy of our method.
Year
DOI
Venue
2004
10.1109/3DPVT.2004.51
3DPVT
Keywords
Field
DocType
accurate reconstruction,ground truth,wide baseline condition,wide baseline images,reconstruction result,different wide baseline surface,new method,reconstruction technique,enhanced surface reconstruction,dense matching,affine propagation method,detailed reconstruction,computational geometry,affinity propagation,image reconstruction,distortion,surface reconstruction
Affine transformation,Iterative reconstruction,Computer vision,Surface reconstruction,Image matching,Computational geometry,Testbed,Ground truth,Artificial intelligence,Distortion,Mathematics
Conference
ISBN
Citations 
PageRank 
0-7695-2223-8
0
0.34
References 
Authors
13
2
Name
Order
Citations
PageRank
Zoltán Megyesi1143.57
Chetverikov, D.295699.89