Abstract | ||
---|---|---|
City environments often lack textured areas, contain repetitive structures, strong lighting changes and there- fore are very difficult for standard 3D modeling pipelines. We present a novel unified framework for creating 3D city models which overcomes these difficulties by exploiting im- age segmentation cues as well as presence of dominant scene orientations and piecewise planar structures. Given panoramic street view sequences, we first demonstrate how to robustly estimate camera poses without a need for bundle adjustment and propose a multi-view stereo method which operates directly on panoramas, while enforcing the piece- wise planarity constraints in the sweeping stage. At last, w e propose a new depth fusion method which exploits the con- straints of urban environments and combines advantages of volumetric and viewpoint based fusion methods. Our tech- nique avoids expensive voxelization of space, operates di- rectly on 3D reconstructed points through effective kd-tre e representation, and obtains a final surface by tessellationof backprojections of those points into the reference image. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/CVPRW.2009.5206535 | CVPR |
Keywords | Field | DocType |
image fusion,image segmentation,solid modelling,stereo image processing,3D city models,3D modeling pipelines,city environment,depth fusion,image segmentation,kd-tree representation,lighting changes,multiview stereo method,panoramic street view sequences,piecewise planar city 3D modeling,piecewise planar structure,piecewise planarity constraint,repetitive structures,scene orientation,space voxelization,street view panoramic sequences,urban environment,viewpoint based fusion,volumetric based fusion | Iterative reconstruction,Computer vision,Pattern recognition,Image fusion,Computer science,Bundle adjustment,Image segmentation,Pixel,Artificial intelligence,3D modeling,3D city models,Piecewise | Conference |
Volume | Issue | ISSN |
2009 | 1 | 1063-6919 |
Citations | PageRank | References |
63 | 3.14 | 18 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Branislav Micusík | 1 | 166 | 10.70 |
Jana Kosecká | 2 | 1523 | 129.85 |