Efficient Multi-View Reconstruction of Large-Scale Scenes using Interest Points, Delaunay Triangulation and Graph Cuts

Labatut, Patrick; Pons, J.-P.; Keriven, Renaud

doi:10.1109/iccv.2007.4408892

Cited by 180 publications

(244 citation statements)

References 30 publications

Supporting

Mentioning

236

Contrasting

Order By: Relevance

“…So our method also has the virtue of the method in paper [19]. In addition, compared to the method in [19], our approach is more efficient and robust.…”

Section: Introductionmentioning

confidence: 82%

See 1 more Smart Citation

Large Scale Scenes Reconstruction from Multiple Views

Shi

Zhang

et al. 2008

2008 International Symposium on Computer Science and Computational Technology

View full text Add to dashboard Cite

Abstract-In this paper, we present a novel method to reconstruct the large scale scenes from multiple calibrated images. It first generates a quasi-dense 3D point cloud of the scene by matching key points across images. Then it builds a tetrahedral decomposition of space by computing the 3D Delaunay triangulation of the 3D point set. Finally, a triangular mesh of the scene is extracted by labeling Delaunay tetrahedra as inside or outside. A globally optimal label assignment is efficiently found as a minimum cut solution in a graph. Experimental results demonstrate the effectiveness of the proposed algorithm.

show abstract

“…So our method also has the virtue of the method in paper [19]. In addition, compared to the method in [19], our approach is more efficient and robust.…”

Section: Introductionmentioning

confidence: 82%

“…Patrick Labatut et al [19] use Delaunay triangulation and graph cuts to reconstruct the large scale scene, and good results are obtained in their experiments. Their method does not require any knowledge of the extent of the scene, and can deal with large-scale scenes at a reasonable computational cost.…”

Section: Introductionmentioning

confidence: 99%

Large Scale Scenes Reconstruction from Multiple Views

Shi

Zhang

et al. 2008

2008 International Symposium on Computer Science and Computational Technology

View full text Add to dashboard Cite

show abstract

“…a building facade or a fountain, then scaled up to much larger scenes, e.g. entire buildings and cities [129,153,97,69]. These major changes were not solely due to the developments in the MVS field itself.…”

Section: Imagery Collectionmentioning

confidence: 99%

Multi-View Stereo: A Tutorial

Furukawa

Hernández

2015

FNT in Computer Graphics and Vision

411

170

View full text Add to dashboard Cite

“…This technique is widely used in standard image segmentation [3,4,5] or in segmentation of range images or stereo matching [6,7]. Several works benefits from graph cuts for 3D mesh segmentation [8,9] or surface extraction [10,11,12]. Segmentation refers to the task of labelling a set of measurements in the 3D object space (point-cloud).…”

Section: Related Workmentioning

confidence: 99%

Graph Cut Based Point-Cloud Segmentation for Polygonal Reconstruction

Sedlacek

Žára

2009

Advances in Visual Computing

View full text Add to dashboard Cite

Abstract. The reconstruction of 3D objects from a point-cloud is based on sufficient separation of the points representing objects of interest from the points of other, unwanted objects. This operation called segmentation is discussed in this paper. We present an interactive unstructured pointcloud segmentation based on graph cut method where the cost function is derived from euclidean distance of point-cloud points. The graph topology and direct 3D point-cloud segmentation are the novel parts of our work. The segmentation is presented on real application, the terrain reconstruction of a complex miniature paper model, the Langweil model of Prague.

show abstract

Efficient Multi-View Reconstruction of Large-Scale Scenes using Interest Points, Delaunay Triangulation and Graph Cuts

Cited by 180 publications

References 30 publications

Large Scale Scenes Reconstruction from Multiple Views

Large Scale Scenes Reconstruction from Multiple Views

Multi-View Stereo: A Tutorial

Graph Cut Based Point-Cloud Segmentation for Polygonal Reconstruction

Contact Info

Product

Resources

About