Globally Consistent Multi-label Assignment on the Ray Space of 4D Light Fields

Wanner, Sven; Straehle, Christoph; Goldluecke, Bastian

doi:10.1109/cvpr.2013.135

Cited by 83 publications

(65 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Quantitative tests on synthetic dense light field dataset showed our approach to be close to the state of the art [1], with a lower complexity. Our approach also shows to be efficient for dense and sparse real light fields from various sources.…”

Section: Resultsmentioning

confidence: 99%

Light Field Segmentation Using a Ray-Based Graph Structure

Hog

Sabater

Guillemot

2016

Computer Vision – ECCV 2016

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

Light Field Segmentation Using a Ray-Based Graph Structure

Hog

Sabater

Guillemot

2016

Computer Vision – ECCV 2016

View full text Add to dashboard Cite

“…7 Light-field analysis has been applied to various problems in computer vision from face recognition 8 to depth estimation. 9 Moreover, successful efforts have been made to bring the light-field technology to the mobile world. 10 To achieve the goal of perfect scale-invariant light field feature description, we first study the effect of scaling on the internal structure of light fields.…”

Section: Briefmentioning

confidence: 99%

Scale-invariant representation of light field images for object recognition and tracking

Ghasemi

Vetterli

2014

SPIE Proceedings

View full text Add to dashboard Cite

We propose a scale-invariant feature descriptor for representation of light-field images. The proposed descriptor can significantly improve tasks such as object recognition and tracking on images taken with recently popularized light field cameras.We test our proposed representation using various light field images of different types, both synthetic and real. Our experiments show very promising results in terms of retaining invariance under various scaling transformations.

show abstract

“…Computer vision tasks such as segmentation, 3 depth map estimation 4 and three-dimensional reconstruction can highly benefit light field information for performance improvement. This requires adaptation of current algorithms to work in the light field space or develop new methods from scratch.…”

Section: Introductionmentioning

confidence: 99%

Computationally efficient background subtraction in the light field domain

2014

View full text Add to dashboard Cite

In this paper we present a novel approach for depth estimation and background subtraction in light field images. our approach exploits the regularity and the internal structure of the light field signal in order to extract an initial depth map of the captured scene and uses the extracted depth map as the input to a final segmentation algorithm which finely isolates the background in the image.Background subtraction is natural application of the light field information since it is highly involved with depth information and segmentation. However many of the approaches proposed so far are not optimized specifically for background subtraction and are highly computationally expensive. Here we propose an approach based on a modified version of the well-known Radon Transform and not involving massive matrix calculations. It is therefore computationally very efficient and appropriate for real-time use.Our approach exploits the structured nature of the light field signal and the information inherent in the plenoptic space in order to extract an initial depth map and background model of the captured scene. We apply a modified the Radon transform and the gradient operator to horizontal slices of the light field signal to infer the initial depth map. The initial depth estimated are further refined to a precise background using a series of depth thresholding and segmentation in ambiguous areas.We test on method on various types real and synthetic of light field images. Scenes with different levels of clutter and also various foreground object depth have been considered in the experiments. The results of our experiments show much better computational complexity while retaining comparable performance to similar more complex methods.

show abstract

Globally Consistent Multi-label Assignment on the Ray Space of 4D Light Fields

Cited by 83 publications

References 22 publications

Light Field Segmentation Using a Ray-Based Graph Structure

Light Field Segmentation Using a Ray-Based Graph Structure

Scale-invariant representation of light field images for object recognition and tracking

Computationally efficient background subtraction in the light field domain

Contact Info

Product

Resources

About