2014 IEEE Conference on Computer Vision and Pattern Recognition 2014
DOI: 10.1109/cvpr.2014.433
|View full text |Cite
|
Sign up to set email alerts
|

Depth Enhancement via Low-Rank Matrix Completion

Abstract: Abstract

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
133
0

Year Published

2016
2016
2021
2021

Publication Types

Select...
6
2

Relationship

0
8

Authors

Journals

citations
Cited by 161 publications
(133 citation statements)
references
References 34 publications
0
133
0
Order By: Relevance
“…Four representative test images, RGBZ_01, RGBZ_03, RGBZ_05, and RGBZ_07, from the RGBZ dataset [23] are used to evaluate the performance. e proposed method is compared with several state-of-the-art [4].…”
Section: Methodsmentioning
confidence: 99%
“…Four representative test images, RGBZ_01, RGBZ_03, RGBZ_05, and RGBZ_07, from the RGBZ dataset [23] are used to evaluate the performance. e proposed method is compared with several state-of-the-art [4].…”
Section: Methodsmentioning
confidence: 99%
“…Inspired by the recent success of low-rank methods application in image processing, e.g., colorization [2], image restoration [16], texture repairing [17] and etc., we develop a depth estimation approach combining matting Laplacian and low-rank method which captures the continuous depth changes while removing texture details intro-http://www.i-joe.org duced by matting Laplacian scheme. We notice that Lu et al [18] also apply low-rank constraints on depth enhancement. The differences between our and their method are: (1) Lu et al [18] assume RGB-D patches lie in a low-dimensional subspace and we apply low-rank regularization to the whole depth-map; (2) the focus of [18] is depthmap completion and our problem is sparse-to-dense depth propagation in semiautomatic 2D to 3D conversion.…”
Section: Related Workmentioning
confidence: 99%
“…We notice that Lu et al [18] also apply low-rank constraints on depth enhancement. The differences between our and their method are: (1) Lu et al [18] assume RGB-D patches lie in a low-dimensional subspace and we apply low-rank regularization to the whole depth-map; (2) the focus of [18] is depthmap completion and our problem is sparse-to-dense depth propagation in semiautomatic 2D to 3D conversion.…”
Section: Related Workmentioning
confidence: 99%
“…This is typically achieved via Markov Random Fields [6,21,7], bilateral filtering [22], layered representations [23], patch-based approaches [10,11], or depth transfer [8,9]. These approaches, however, inherently assume to have access to regularly-spaced depth measurements, and thus cannot handle large holes in depth maps.…”
Section: Related Workmentioning
confidence: 99%
“…For instance, depth super-resolution [6][7][8][9][10][11] tackles the sparseness issue and attempts to densify the observed depth data. Typically, however, existing methods assume that the measurements are regularly spaced, and are thus ill-suited to handle large holes.…”
Section: Introductionmentioning
confidence: 99%