Accurate, Dense, and Robust Multi-View Stereopsis
Authors:
- 1 June 2007
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 1-8
Abstract
This paper proposes a novel algorithm for calibrated multi-view stereopsis that outputs a (quasi) dense set of rectangular patches covering the surfaces visible in the input images. This algorithm does not require any initialization in the form of a bounding volume, and it detects and discards automatically outliers and obstacles. It does not perform any smoothing across nearby features, yet is currently the top performer in terms of both coverage and accuracy for four of the six benchmark datasets presented in [20]. The keys to its performance are effective techniques for enforcing local photometric consistency and global visibility constraints. Stereopsis is implemented as a match, expand, and filter procedure, starting from a sparse set of matched keypoints, and repeatedly expanding these to nearby pixel correspondences before using visibility constraints to filter away false matches. A simple but effective method for turning the resulting patch model into a mesh appropriate for image-based modeling is also presented. The proposed approach is demonstrated on various datasets including objects with fine surface details, deep concavities, and thin structures, outdoor scenes observed from a restricted set of viewpoints, and "crowded" scenes where moving obstacles appear in different places in multiple images of a static structure of interest.Keywords
This publication has 9 references indexed in Scilit:
- A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms2006
- Multi-View Stereo Revisited2006
- Combined Depth and Outlier Estimation in Multi-View Stereo2006
- A Surface Reconstruction Method Using Global Graph Cut OptimizationInternational Journal of Computer Vision, 2006
- Hierarchical Volumetric Multi-view Stereo Reconstruction of Manifold Surfaces based on Dual Graph Embedding2006
- Multi-View Stereo via Volumetric Graph-Cuts2005
- A survey of point-based techniques in computer graphicsComputers & Graphics, 2004
- Photorealistic scene reconstruction by voxel coloring2002
- ‘Region-growing’ algorithm for matching of terrain imagesImage and Vision Computing, 1989