1998
DOI: 10.1109/34.730555
|View full text |Cite
|
Sign up to set email alerts
|

Inference of integrated surface, curve and junction descriptions from sparse 3D data

Abstract: Abstract-We are interested in descriptions of 3D data sets, as obtained from stereo or a 3D digitizer. We therefore consider as input a sparse set of points, possibly associated with certain orientation information. In this paper, we address the problem of inferring integrated high-level descriptions such as surfaces, 3D curves, and junctions from a sparse point set. While the method proposed by Guy and Medioni provides excellent results for smooth structures, it only detects surface orientation discontinuitie… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
7
0

Year Published

1999
1999
2015
2015

Publication Types

Select...
4
2
1

Relationship

0
7

Authors

Journals

citations
Cited by 55 publications
(7 citation statements)
references
References 20 publications
0
7
0
Order By: Relevance
“…The only input parameter of the proposed method is the voting range. Fortunately, the tensor voting results are not very sensitive to the values of the voting range [9,10]. Table 4 shows the SNR performance of the proposed method with different values of the voting range.…”
Section: Resultsmentioning
confidence: 99%
See 3 more Smart Citations
“…The only input parameter of the proposed method is the voting range. Fortunately, the tensor voting results are not very sensitive to the values of the voting range [9,10]. Table 4 shows the SNR performance of the proposed method with different values of the voting range.…”
Section: Resultsmentioning
confidence: 99%
“…The tensor voting framework [9,10], which is very robust to noise, is used to smooth the input motion vector field by applying a voting process among the tensors representing the motion vectors. The outlier motion vectors can be easily detected by comparing the input motion vectors with the corresponding ones in the smoothed motion vector field.…”
Section: Overview Of the Methodsmentioning
confidence: 99%
See 2 more Smart Citations
“…In this section, the original tensor voting (OTV) formulation [3][4][5] is reviewed. The general outline of the technique is initially presented without mathematical rigour to show the procedure from a high-level perspective.…”
Section: Original Tensor Votingmentioning
confidence: 99%