A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Pattern recognition for high performance imaging
2018
Pattern Recognition
Preserved Fulltext
Acknowledgments We would like to thank all the authors for their valuable contributions to this special issue. ...
We would like also to thank all reviewers for dedicated work which guarantees the high quality of accepted papers. We would like to express our gratitude to the Editor-in-Chief, Prof. ...
In the article "Occlusion-Aware Depth Estimation for Light Field Using Multi-Orientation EPIs", the authors extract epipolar plane images in all available directions to make full use of the regular grid ...
doi:10.1016/j.patcog.2018.04.021
fatcat:zzyphganvne3fny357kgjznd3a
Depth from Combining Defocus and Correspondence Using Light-Field Cameras
2013
2013 IEEE International Conference on Computer Vision
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2015; you can also visit the original URL.
The file type is application/pdf.
In this paper, we present a novel simple and principled algorithm that computes dense depth estimation by combining both defocus and correspondence depth cues. ...
We then show how to combine the two cues into a high quality depth map, suitable for computer vision applications such as matting, full control of depth-of-field, and surface reconstruction. ...
Acknowledgements This work was funded by ONR PECASE grant N00014-09-1-0741, and an NSF fellowship to M. Tao. We are grateful for the support from Nokia, Samsung, and Adobe. ...
doi:10.1109/iccv.2013.89
dblp:conf/iccv/TaoHMR13
fatcat:ptag5qxxkvgldmeaoi7iyo4whu
EPI-based Oriented Relation Networks for Light Field Depth Estimation
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
The spatial and angular information implicitly contain geometrical characteristics such as multi-view or epipolar geometry, which can be exploited to improve the performance of depth estimation. ...
An Epipolar Plane Image (EPI), the unique 2D spatial-angular slice of the light field, contains patterns of oriented lines. The slope of these lines is associated with the disparity. ...
The light field refocusing shifts the sub-aperture images to obtain images focused at different depth planes [1] . ...
arXiv:2007.04538v2
fatcat:riddw7xkyvdutjbjwasussgozy
Review of light field technologies
2021
Visual Computing for Industry, Biomedicine, and Art
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
In this article, light field imaging is reviewed from the following aspects with an emphasis on the achievements of the past five years: (1) depth estimation, (2) content editing, (3) image quality, (4 ...
) scene reconstruction and view synthesis, and (5) industrial products because the technologies of lights fields also intersect with industrial applications. ...
Acknowledgements The authors are grateful to Kuaishou Technology, University of California, Berkeley, and Tsinghua University. ...
doi:10.1186/s42492-021-00096-8
pmid:34862574
pmcid:PMC8642475
fatcat:6rq5rx5svrcerdr7rciaijy3k4
Occlusion-Aware Depth Estimation Using Light-Field Cameras
2015
2015 IEEE International Conference on Computer Vision (ICCV)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
By treating these two regions separately, depth estimation can be improved. Occlusion predictions can also be computed and used for regularization. ...
Consumer-level and high-end light-field cameras are now widely available. Recent work has demonstrated practical methods for passive depth estimation from light-field images. ...
Acknowledgement We acknowledge support from ONR grant N00014-15-1-2013, a Berkeley Fellowship, Intel, and funding from Sony to the UC San Diego Center for Visual Computing. ...
doi:10.1109/iccv.2015.398
dblp:conf/iccv/WangER15
fatcat:722f5ojy7jdyjk7w2yirn3kubi
Depth Estimation for Lytro Images by Adaptive Window Matching on EPI
2017
Journal of Imaging
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
A depth estimation algorithm from plenoptic images is presented. There are two stages to estimate the depth. First is the initial estimation base on the epipolar plane images (EPIs). ...
An energy function keeps the data similar to the original estimation, and then the data are smoothed by minimizing the second derivative. Depth values should satisfy consistency across multiple views. ...
Abbreviations The following abbreviations are used in this manuscript:
EPI Epipolar Plane Image MRF Markov Random Field ...
doi:10.3390/jimaging3020017
fatcat:rpa4nhfv5zaqxhngvsq5avkcwq
Depth Estimation of Semi-submerged Objects Using a Light-Field Camera
2017
2017 14th Conference on Computer and Robot Vision (CRV)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Existing hand-held consumer light field cameras are well-suited for automated refocusing, depth detection in outdoor environment. ...
for semisubmerged objects using an image from a light field camera. ii First and foremost, I would like to express my sincere gratitude to my supervisor, Dr. ...
potential of depth estimation using epipolar plane image, such like [22] [15] [23] . ...
doi:10.1109/crv.2017.44
dblp:conf/crv/FanY17
fatcat:g55ii3oh6nhingqb7l6zrssqd4
Occlusion-Model Guided Antiocclusion Depth Estimation in Light Field
2017
IEEE Journal on Selected Topics in Signal Processing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2016 pre-print arXiv:1608.04187v1 fatcat:jtb3rweb7zd37b6x723owrsxcqOther Versions
Occlusion is one of the most challenging problems in depth estimation. ...
Previous work has modeled the single-occluder occlusion in light field and get good results, however it is still difficult to obtain accurate depth for multi-occluder occlusion. ...
[15, 16] applies structure tensor to analyze the Epipolar Plane Image (EPI). ...
doi:10.1109/jstsp.2017.2730818
fatcat:zy5moyvkynbqxfhm3c7ysyqhue
External Mask Based Depth and Light Field Camera
2013
2013 IEEE International Conference on Computer Vision Workshops
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
A consequence of our design is that the external aperture causes heavy vignetting in the acquired images. We calibrate the mask parameters and estimate multi-view scene depth under vignetting. ...
In addition to depth, we show light field applications such as refocusing and defocus blur at the sensor resolution. ...
Reddy and R. Ramamoorthi were supported by ONR PECASE grant N00014-09-1-0741. J. Bai was supported by A*STAR NSS PhD fellowship. We also acknowledge support and funding from Samsung and Nokia. ...
doi:10.1109/iccvw.2013.12
dblp:conf/iccvw/ReddyBR13
fatcat:tafjmarkvreszgx732lwalb5oi
Occlusion-aware Unsupervised Learning of Depth from 4-D Light Fields
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Depth estimation is a fundamental issue in 4-D light field processing and analysis. ...
angular coherence among subsets of the light field views to estimate initial depth maps, and utilize a constrained unsupervised loss to learn their corresponding reliability for final depth prediction ...
Traditional methods for LF depth estimation mainly design different costs to explore the depth cues intrinsically provided by the LF data [6] , such as detecting the lines in the epipolar plane images ...
arXiv:2106.03043v2
fatcat:5hpvnuvn35fx5lhppqtwxghdri
Simultaneous Color Restoration and Depth Estimation in Light Field Imaging
2022
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Experimental results show that both image interpolation quality and depth estimation can benefit from their interaction, mainly for processes such as image demosaicing which are shown to be sensitive to ...
In this paper, we address the interaction between color interpolation and depth estimation in light field, and propose a probabilistic approach to handle these two processing steps jointly. ...
There are mainly two challenges for EPI-based methods: occlusion handling and line ambiguity. Huang et al. ...
doi:10.1109/access.2022.3172343
fatcat:jy46ghirtzgsbasgrsm5w4wxs4
Learning to Think Outside the Box: Wide-Baseline Light Field Depth Estimation with EPI-Shift
2019
2019 International Conference on 3D Vision (3DV)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2019 pre-print arXiv:1909.09059v1 fatcat:kvawngyffncb3cfkoy2qsl7kkq
We propose a method for depth estimation from light field data, based on a fully convolutional neural network architecture. ...
Our goal is to design a pipeline which achieves highly accurate results for small- and wide-baseline light fields. ...
We thank the Center for Information Services and High Performance Computing (ZIH) at TU Dresden for generous allocations of computer time. ...
doi:10.1109/3dv.2019.00036
dblp:conf/3dim/LeistnerSMGR19
fatcat:eewtvohxjzexvhxd6zvhqugojm
Total variation-based dense depth from multicamera array
2018
Optical Engineering: The Journal of SPIE
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Other Versions
The proposed framework utilizes analysis of the local Epipolar Plane Image (EPI) to initiate the depth estimation process. ...
Current depth estimation methods provide useful estimations of depth in an imaged scene but are often impractical due to significant computational requirements. ...
Later, the depth map is estimated based on the calibration details of the camera and it is used to reconstruct the Epipolar images. The reconstructed Epipolar images are used for refocusing purposes. ...
doi:10.1117/1.oe.57.6.063105
fatcat:s4vzixo6abhghek4e7j4ssx5em
Occlusion Handling by Successively Excluding Foregrounds for Light Field Depth Estimation based on Foreground-Background Separation
2021
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Concurrently, Dosovitskiy et al. [22] proposed an end-to-end method for disparity estimation, which can be considered as a depth model-based method. ...
Although there have been widely studied to handle the occlusion problem with the cost-based method, there are not enough researches to handle the occlusion problem with the FBS-based methods yet. ...
In view of the LF representation, the local DFLF methods could be categorized according to LF representation used for derivations of the depth information: the epipolar plane image (EPI)-based methods, ...
doi:10.1109/access.2021.3098819
fatcat:f63a5gcsivet5dqzplj6bao4qi
Removing Dynamic Objects for Static Scene Reconstruction using Light Fields
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We simultaneously estimate both the depth and the refocused image of the static scene using semantic segmentation for detecting dynamic objects in a single time step. ...
In this paper we present a method to synthesize a refocused image of the static background in the presence of dynamic objects that uses a light-field acquired with a linear camera array. ...
We would like to thank Srikumar Ramalingam, Alex Techet and Abhishek Bajpayee for helping guide our efforts and the members of the Northeastern Field Robotics lab for their help with data collection. ...
arXiv:2003.11076v1
fatcat:6h7pvt7mbjcr5dnosllhycixya
« Previous
Showing results 1 — 15 out of 103 results