Filters








42,102 Hits in 6.3 sec

Total variation-based dense depth from multicamera array

Hossein Javidnia, Peter Corcoran
2018 Optical Engineering: The Journal of SPIE  
This paper presents a novel framework that generates a high-quality continuous depth map from multi-camera array/light field cameras.  ...  Evaluation of this method based on a well-known benchmark indicates that the proposed framework performs well in terms of accuracy when compared to the top-ranked depth estimation methods and a baseline  ...  Light Field Depth Estimation and Stereo Framework Kim et al. [30] proposed a framework to generate stereo images from a set of light field data.  ... 
doi:10.1117/1.oe.57.6.063105 fatcat:s4vzixo6abhghek4e7j4ssx5em

Attention-Based View Selection Networks for Light-Field Disparity Estimation

Yu-Ju Tsai, Yu-Lun Liu, Ming Ouhyoung, Yung-Yu Chuang
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
This paper introduces a novel deep network for estimating depth maps from a light field image.  ...  Experiments show that the proposed method achieves state-of-the-art performance in terms of accuracy and ranks the first on a popular benchmark for disparity estimation for light field images.  ...  Acknowledgements This work was supported in part by Ministry of Science and Technology (MOST) and MOST Joint Research Center for  ... 
doi:10.1609/aaai.v34i07.6888 fatcat:bkebmzfv3jbjrhzh2d4aay3fku

Fast and Efficient Depth Map Estimation from Light Fields [article]

Yuriy Anisimov, Didier Stricker
2018 arXiv   pre-print
The paper presents an algorithm for depth map estimation from the light field images in relatively small amount of time, using only single thread on CPU.  ...  The proposed method improves existing principle of line fitting in 4-dimensional light field space. Line fitting is based on color values comparison using kernel density estimation.  ...  The authors are grateful to Vladislav Golyanik, Kiran Varanasi and Jonathan Wray for the provided help.  ... 
arXiv:1805.00264v1 fatcat:ork5dh2xtzdupmo75ld6wzxjka

Light Field Intrinsics with a Deep Encoder-Decoder Network

Anna Alperovich, Ole Johannsen, Michael Strecke, Bastian Goldluecke
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
We present a fully convolutional autoencoder for light fields, which jointly encodes stacks of horizontal and vertical epipolar plane images through a deep network of residual layers.  ...  We provide an extensive evaluation on synthetic light field data, and show that the network yields good results on previously unseen real world data captured by a Lytro Illum camera and various gantries  ...  Acknowledgments This work was supported by the ERC Starting Grant "Light Field Imaging and Analysis" (LIA 336978, FP7-2014).  ... 
doi:10.1109/cvpr.2018.00953 dblp:conf/cvpr/AlperovichJSG18 fatcat:hxboolz3bnfxfhmzw7divribxa

Rapid Light Field Depth Estimation with Semi-Global Matching [article]

Yuriy Anisimov, Oliver Wasenmüller, Didier Stricker
2019 arXiv   pre-print
Running time of the light field depth estimation algorithms is typically high. This assessment is based on the computational complexity of existing methods and the large amounts of data involved.  ...  In this context, we propose an approach, which involves Semi-Global Matching for the processing of light field images.  ...  The authors are grateful to Kiran Varanasi and Jonathan Wray for the provided support.  ... 
arXiv:1907.13449v1 fatcat:ctokovsfbzd77dwl5fvlrhzlyy

Learning to Think Outside the Box: Wide-Baseline Light Field Depth Estimation with EPI-Shift

Titus Leistner, Hendrik Schilling, Radek Mackowiak, Stefan Gumhold, Carsten Rother
2019 2019 International Conference on 3D Vision (3DV)  
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

Fast Depth Estimation for Light Field Cameras

Kazu Mishiba
2020 IEEE Transactions on Image Processing  
As most of these applications use depth information, depth estimation from a light field image is an important topic for light field image processing research.  ...  Fast Depth Estimation for Light Field Cameras Kazu Mishiba , Member, IEEE Abstract-Fast depth estimation for light field images is an important task for multiple applications such as image-based rendering  ... 
doi:10.1109/tip.2020.2970814 fatcat:s55cax4fabgzthwvhzgnovb464

Fast and Accurate 3D Measurement Based on Light-Field Camera and Deep Learning

Haoxin Ma, Zhiwen Qian, Tingting Mu, Shengxian Shi
2019 Sensors  
from one single light-field image captured by one single light-field camera.  ...  Meanwhile, our network has achieved similar or better performance in other regions for both synthetic light-field images and real-world data compared to the state-of-the-art algorithms.  ...  With these advantages, various algorithms [6] [7] [8] have been developed to estimate depth information from single light-field image.  ... 
doi:10.3390/s19204399 fatcat:34nbga2iwbfchpscq63s44fwae

Deep Depth From Focus [article]

Caner Hazirbas, Sebastian Georg Soyer, Maximilian Christian Staab, Laura Leal-Taixé, Daniel Cremers
2018 arXiv   pre-print
In this paper, we propose 'Deep Depth From Focus (DDFF)' as the first end-to-end learning approach to this problem. One of the main challenges we face is the hunger for data of deep neural networks.  ...  In order to obtain a significant amount of focal stacks with corresponding groundtruth depth, we propose to leverage a light-field camera with a co-calibrated RGB-D sensor.  ...  for DFF, but also for other tasks such as depth from light-field or 3d reconstruction from light-field.  ... 
arXiv:1704.01085v3 fatcat:6rcoj7xlzvaghdpdbfw4m75baq

Trust your Model: Light Field Depth Estimation with Inline Occlusion Handling

Hendrik Schilling, Maximilian Diebold, Carsten Rother, Bernd Jahne
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
We address the problem of depth estimation from lightfield images. Our main contribution is a new way to handle occlusions which improves general accuracy and quality of object borders.  ...  We have evaluated our method on a public light-field dataset, where we achieve state-of-the-art results in nine out of twelve error metrics, with a close tie for the remaining three.  ...  for Image Processing (HCI).  ... 
doi:10.1109/cvpr.2018.00476 dblp:conf/cvpr/SchillingDRJ18 fatcat:q6h3ymaxi5hnxktxis5p3sdvce

Nonlinear Optimization of Light Field Point Cloud

Yuriy Anisimov, Jason Raphael Rambach, Didier Stricker
2022 Sensors  
Light field depth estimation utilizes many observations of the scene and hence can provide accurate reconstruction.  ...  Together with that we reformulate the reconstruction result to a form of point cloud from different light field viewpoints and propose a non-linear optimization of it.  ...  Related Work Many methods exist for solving the light field depth estimation task.  ... 
doi:10.3390/s22030814 pmid:35161563 pmcid:PMC8838410 fatcat:tr4kfymnqbhmldq6bgkx6tshf4

Light Field Salient Object Detection: A Review and Benchmark [article]

Keren Fu, Yao Jiang, Ge-Peng Ji, Tao Zhou, Qijun Zhao, Deng-Ping Fan
2021 arXiv   pre-print
Besides, due to the inconsistency of datasets in their current forms, we further generate complete data and supplement focal stacks, depth maps and multi-view images for the inconsistent datasets, making  ...  This paper provides the first comprehensive review and benchmark for light field SOD, which has long been lacking in the saliency community.  ...  The light-field flow was first employed in this method, estimated from focal stacks and multi-view sequences, to capture depth discontinuities/contrast.  ... 
arXiv:2010.04968v4 fatcat:gvwnnhd4m5hlfjaamuupe7ymva

EPI-based Oriented Relation Networks for Light Field Depth Estimation [article]

Kunyuan Li, Jun Zhang, Rui Sun, Xudong Zhang, Jun Gao
2020 arXiv   pre-print
Benefiting from this property of EPIs, some representative methods estimate depth maps by analyzing the disparity of each line in EPIs.  ...  To facilitate training, we also propose a refocusing-based data augmentation method to obtain different slopes from EPIs of the same scene point.  ...  of depth estimation from light fields.  ... 
arXiv:2007.04538v2 fatcat:riddw7xkyvdutjbjwasussgozy

BOP: Benchmark for 6D Object Pose Estimation [article]

Tomas Hodan, Frank Michel, Eric Brachmann, Wadim Kehl, Anders Glent Buch, Dirk Kraft, Bertram Drost, Joel Vidal, Stephan Ihrke, Xenophon Zabulis, Caner Sahin, Fabian Manhardt, Federico Tombari (+2 others)
2018 arXiv   pre-print
We propose a benchmark for 6D pose estimation of a rigid object from a single RGB-D input image.  ...  The training data consists of a texture-mapped 3D object model or images of the object in known 6D poses.  ...  , No. 16-072105: Complex network methods applied to ancient Egyptian data in the Old Kingdom (2700-2180 BC).  ... 
arXiv:1808.08319v1 fatcat:k6bmka24ybdytnzxdf2vbcco6q

BOP: Benchmark for 6D Object Pose Estimation [chapter]

Tomáš Hodaň, Frank Michel, Eric Brachmann, Wadim Kehl, Anders Glent Buch, Dirk Kraft, Bertram Drost, Joel Vidal, Stephan Ihrke, Xenophon Zabulis, Caner Sahin, Fabian Manhardt (+4 others)
2018 Lecture Notes in Computer Science  
We propose a benchmark for 6D pose estimation of a rigid object from a single RGB-D input image.  ...  The training data consists of a texture-mapped 3D object model or images of the object in known 6D poses.  ...  , No. 16-072105: Complex network methods applied to ancient Egyptian data in the Old Kingdom (2700-2180 BC).  ... 
doi:10.1007/978-3-030-01249-6_2 fatcat:vfcllj6debaznkp3gdg7frfbwm
« Previous Showing results 1 — 15 out of 42,102 results