ACM SIGGRAPH 2004 Papers 2004
DOI: 10.1145/1186562.1015814
|View full text |Cite
|
Sign up to set email alerts
|

Context-based surface completion

Abstract: Figure 1: Completing a hole in a point-based model. In the darker colored region we removed sample points to demonstrate the surface completion technique. In the middle right the region is filled with a smooth patch conforming with the densely sampled areas, and the result of our context-based surface completion is on the right. AbstractSampling complex, real-world geometry with range scanning devices almost always yields imperfect surface samplings. These "holes" in the surface are commonly filled with a smoo… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
122
0
2

Year Published

2005
2005
2017
2017

Publication Types

Select...
5
3
1

Relationship

0
9

Authors

Journals

citations
Cited by 104 publications
(125 citation statements)
references
References 23 publications
0
122
0
2
Order By: Relevance
“…Disocclusion of a scene has only been scarcely investigated for 3D point clouds (Sharf et al, 2004, Park et al, 2005, Becker et al, 2009. These methods mostly work on complete point clouds rather than LiDAR point clouds.…”
Section: Disocclusionmentioning
confidence: 99%
“…Disocclusion of a scene has only been scarcely investigated for 3D point clouds (Sharf et al, 2004, Park et al, 2005, Becker et al, 2009. These methods mostly work on complete point clouds rather than LiDAR point clouds.…”
Section: Disocclusionmentioning
confidence: 99%
“…In fact, most of these approaches do not use enough geometric information available on the surrounding mesh. This is not true for the context-based surface completion algorithm of [29] where the inner mesh is defined according to shapes that can be very far from the hole. But their process may lead to very unexpected results.…”
Section: Related Workmentioning
confidence: 99%
“…We use the graph cut technique, which was originally used [16] to find a minimum cut-ting path and has since been extended to other applications in image and geometry processing, especially in texturing and video synthesis [16,2,27,28], foreground removal [29], image blending [30] and geometric processing [31,32]. The schematic diagram in Figure 7 shows a region of overlap between two image patches A and B.…”
Section: Graph Cutmentioning
confidence: 99%