Filters








2,454 Hits in 15.9 sec

Automatic Augmentation and Meshing of Sparse 3D Scene Structure

O. Cooper, N. Campbell, D. Gibson
<span title="">2005</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wsjivbkuezdvxdnrhihbwjrxlu" style="color: black;">2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION&#39;05) - Volume 1</a> </i> &nbsp;
We propose a novel method of robustly and automatically creating surface meshes from the very sparsely populated 3D point clouds typically produced by Structure from Motion algorithms.  ...  Prior to meshing the point cloud is augmented with new points created by planar intersection thus improving the subsequent reconstruction of edges and corners in the scene.  ...  This ensures that simple but good quality meshes are created automatically from the sparse 3D scene structure produced by Structure from Motion.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/acvmot.2005.28">doi:10.1109/acvmot.2005.28</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/wacv/CooperCG05.html">dblp:conf/wacv/CooperCG05</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nj7hrgacpzhjlme4ulzrgewlxe">fatcat:nj7hrgacpzhjlme4ulzrgewlxe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20060511211253/http://www.cs.bris.ac.uk:80/Publications/Papers/2000196.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/6b/9c/6b9c53f65f3117ed0e2dc24054c9cdc24e1f068d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/acvmot.2005.28"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Semantic 3D Models from Real World Scene Recordings for Traffic Accident Simulation

Ludwig Mohr, Martin Öttl, Michael Haberl, Matthias Rüther, Horst Bischof
<span title="2018-04-16">2018</span> <i title="Zenodo"> Zenodo </i> &nbsp;
We present an enclosed pipeline generating 3D objects, their extents and relative positions as well as their semantic class from a combination of photogrammetric recordings and LiDAR (Light Detection And  ...  By adjusting the desired level of detail, these objects are suitable for both direct integration into the 3D scene reconstruction for use in the accident simulation software PC-Crash, as well as for fine  ...  Acknowledgements This study is part of the project IMPROVE and is financially supported by the FFG, the Austrian Research Promotion Agency of the Austrian Federal Ministry for Transport, Innovation and  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5281/zenodo.1487620">doi:10.5281/zenodo.1487620</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mniny6y4fvgybgm2d2mkjn4egi">fatcat:mniny6y4fvgybgm2d2mkjn4egi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220129161322/https://zenodo.org/record/1487621/files/Contribution_11192_fullpaper.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/70/d4/70d4149446022124f3e27ffa71b7a3cd35392d00.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5281/zenodo.1487620"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> zenodo.org </button> </a>

Synthesizing reality for realistic physical behavior of virtual objects in augmented reality applications for smart-phones

Nir Amar, Meir Raviv, Barak David, Oleg Chernoguz, Jihad El-Sana
<span title="">2013</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/vufiov5gf5gqzn5pb6uctytdja" style="color: black;">2013 IEEE Virtual Reality (VR)</a> </i> &nbsp;
This paper presents a framework for augmented reality applications that runs on smart mobile phones and enables realistic physical behavior of the virtual objects in the real-world.  ...  The two images are used to reconstruct a 3D representation of the real world, which is good enough to enable physical interaction between the virtual and the real-world objects, but not fine enough to  ...  structure, and embedding the virtual objects into the synthesized scene.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/vr.2013.6549393">doi:10.1109/vr.2013.6549393</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/vr/AmarRDCE13.html">dblp:conf/vr/AmarRDCE13</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/f3e33clky5hxjl2dl45qwbj3li">fatcat:f3e33clky5hxjl2dl45qwbj3li</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20130409151735/http://www.cs.bgu.ac.il/~el-sana/publications/pdf/Mobile3DAR.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/42/d6/42d62627e8e6cd2babaf89f97441873864d18ad7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/vr.2013.6549393"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Exploiting Repetitions for Image-Based Rendering of Facades

Simon Rodriguez, Adrien Bousseau, Fredo Durand, George Drettakis
<span title="">2018</span> <i title="Wiley"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/p2lpq6bugfcqxk44anrm6yki4m" style="color: black;">Computer graphics forum (Print)</a> </i> &nbsp;
Our detailed 3D mesh, augmented set of views, and reflection mask enable image-based rendering of much higher quality than results obtained using the input images directly.  ...  a) Input (b) Repetitive Window (c) 3D Mesh and Reflection Mask (d) Image-Based Rendering Naive IBR Naive IBR Our result Our result Figure 1: Given a small number of pictures of a facade (a), we augment  ...  from Technicolor and Adobe.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1111/cgf.13480">doi:10.1111/cgf.13480</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/av2rkubw55bptaeilxnlao7yge">fatcat:av2rkubw55bptaeilxnlao7yge</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180722232852/http://www-sop.inria.fr/reves/Basilic/2018/RBDD18/rodriguez2018exploitingrepetitionsforibr.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/b6/f2/b6f2c8d82f73608a0c90191cc6adb495b30c669b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1111/cgf.13480"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Creating Textured 3D Models from Image Collections using Open Source Software

Ali Alouache, Xiaolan Yao, Qinghe Wu
<span title="2017-04-17">2017</span> <i title="Foundation of Computer Science"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/b637noqf3vhmhjevdfk3h5pdsu" style="color: black;">International Journal of Computer Applications</a> </i> &nbsp;
At first, we use VisualSFM which is a robust Structure from Motion software estimating the calibration parameters of all the images, and a sparse 3D point cloud.  ...  The creation of digital three dimensional (3D) spatial models for the real scenes using image collections is one of the interesting applications of computer vision.  ...  It is a multiview stereo software that takes a set of images and camera parameters as input and reconstructs the 3D structure of the scene as a dense points cloud.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5120/ijca2017913734">doi:10.5120/ijca2017913734</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/h74hv72vafezppzdlxraoi77ve">fatcat:h74hv72vafezppzdlxraoi77ve</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180603195152/https://www.ijcaonline.org/archives/volume163/number9/alouache-2017-ijca-913734.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/07/d5/07d5f8b74c30bd0818fa61edf6b89eeabf0911b6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5120/ijca2017913734"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Reducing the gap between Augmented Reality and 3D modeling with real-time depth imaging

Svenja Kahn
<span title="2011-12-23">2011</span> <i title="Springer Nature"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/rme7udioofgshaoo2sgnhqfxpa" style="color: black;">Virtual Reality</a> </i> &nbsp;
The proposed method detects the differences between a scene and a 3D model of the scene in real time.  ...  Whereas 3D surface models are often used for augmented reality (e.g., for occlusion handling or modelbased camera tracking), the creation and the use of such dense 3D models in augmented reality applications  ...  no possibility to automatically compare the 3D data of the model with the 3D geometry of the real scene.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s10055-011-0203-0">doi:10.1007/s10055-011-0203-0</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/sei7vgbdwrb4di5p7r43jmyfv4">fatcat:sei7vgbdwrb4di5p7r43jmyfv4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170808143954/https://www.igd.fraunhofer.de/sites/default/files/media/biblio/2013/2013-kahn-reducing-gap-ar-3dmodeling.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/48/2f/482fb8b7ab450646f9cbf99397543efd24fe7383.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s10055-011-0203-0"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Augmented Reality for Depth Cues in Monocular Minimally Invasive Surgery [article]

Long Chen, Wen Tang, Nigel W. John, Tao Ruan Wan, Jian Jun Zhang
<span title="2017-03-01">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
However, robust 3D surface reconstruction and augmented reality with depth perception on the reconstructed scene are yet to be reported. This paper presents our work in this area.  ...  We then develop a robust global 3D surface reconstruction frame- work based on the sparse point clouds extracted from the SLAM framework.  ...  Unstructured sparse point clouds, however, describe the 3D structure of the endoscopic scene poorly.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1703.01243v1">arXiv:1703.01243v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/htooo2kfvfamhp3ud5r5krdpd4">fatcat:htooo2kfvfamhp3ud5r5krdpd4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200903132350/https://arxiv.org/pdf/1703.01243v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/40/5b/405b5e597529a9fd85206395d679df8fcff465f6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1703.01243v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

SLAM-based dense surface reconstruction in monocular Minimally Invasive Surgery and its application to Augmented Reality

Long Chen, Wen Tang, Nigel W. John, Tao Ruan Wan, Jian Jun Zhang
<span title="">2018</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/yejgm3i4j5ehxbahbzb42nncke" style="color: black;">Computer Methods and Programs in Biomedicine</a> </i> &nbsp;
Augmented Reality (AR) technology can help to overcome these limitations by augmenting the real scene with annotations, labels, tumour measurements or even a 3D reconstruction of anatomy structures at  ...  Finally, the 3D geometric information of the surgical scene allows better understanding and accurate placement AR augmentations based on a robust 3D calibration.  ...  by displaying 3D mesh structures when performing monocular endoscope procedures.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.cmpb.2018.02.006">doi:10.1016/j.cmpb.2018.02.006</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/29544779">pmid:29544779</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/v4bhbs7wzzej7pifadeffhwzqm">fatcat:v4bhbs7wzzej7pifadeffhwzqm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200307132546/https://bradscholars.brad.ac.uk/bitstream/handle/10454/15362/chen_et_al_2018.pdf;jsessionid=186466DA48C9D8FA4736FB1B0FD8E629?sequence=3" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/9c/40/9c407cc08d51f687db7b8400140d9a1011296fd5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.cmpb.2018.02.006"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera [article]

Iro Armeni, Zhi-Yang He, JunYoung Gwak, Amir R. Zamir, Martin Fischer, Jitendra Malik, Silvio Savarese
<span title="2019-10-06">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Aspiring to have one unified structure that hosts diverse types of semantics, we follow the Scene Graph paradigm in 3D, generating a 3D Scene Graph.  ...  Given a 3D mesh and registered panoramic images, we construct a graph that spans the entire building and includes semantics on objects (e.g., class, material, and other attributes), rooms (e.g., scene  ...  We augment the basic scene graph structure, such as the one in Visual Genome [27] , with essential 3D information and generate a 3D Scene Graph.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1910.02527v1">arXiv:1910.02527v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ipibuqyurbgkvkumc75eaj3jvi">fatcat:ipibuqyurbgkvkumc75eaj3jvi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200829205103/https://arxiv.org/pdf/1910.02527v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/77/b4/77b4f542ea56b02804672790b6482df400428c95.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1910.02527v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Live dense reconstruction with a single moving camera

Richard A. Newcombe, Andrew J. Davison
<span title="">2010</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition</a> </i> &nbsp;
We take point-based real-time structure from motion (SFM) as our starting point, generating accurate 3D camera pose estimates and a sparse point cloud.  ...  the 3D scene and are correctly clipped by occlusions.  ...  We are very grateful to Murray Shanahan, Steven Lovegrove, Thomas Pock, Andreas Fidjeland, Alexandros Bouganis, Owen Holland and others for helpful discussions and software collaboration.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2010.5539794">doi:10.1109/cvpr.2010.5539794</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/NewcombeD10.html">dblp:conf/cvpr/NewcombeD10</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7b7yvrjlv5aipcurmtvj6xjxfa">fatcat:7b7yvrjlv5aipcurmtvj6xjxfa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20110401063926/http://www.doc.ic.ac.uk/~ajd/Publications/newcombe_davison_cvpr2010.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/1c/8b/1c8bbb289447958d690f0ee4bfe9a355e20fa3c1.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2010.5539794"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Efficient Visualization of Architectural Models from a Structure and Motion Pipeline [article]

Michela Farenzena, Andrea Fusiello, Riccardo Gherardi
<span title="">2008</span> <i title="The Eurographics Association"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/xgoygnj3knbt3jsqqs5uay37ba" style="color: black;">Eurographics State of the Art Reports</a> </i> &nbsp;
We propose to augment a typical structure from motion pipeline with two additional steps, automatic fitting of high-level solid primitives and relief maps extraction, thus recovering both the overall structure  ...  This not only gives birth to a more tractable and semantic model of the imaged scene, but allows for efficient and compelling rendering.  ...  Reconstruction pipeline a collection of uncalibrated images of the same scene, with constant intrinsic parameters, we aim to recover camera parameters, pose estimates and a sparse 3D points cloud of the  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2312/egs.20081029">doi:10.2312/egs.20081029</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jbnus25ddfcm7lsi4h7x3bdyea">fatcat:jbnus25ddfcm7lsi4h7x3bdyea</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220117183902/https://diglib.eg.org/xmlui/bitstream/handle/10.2312/egs.20081029.091-094/091-094.pdf;jsessionid=1BD1325DFD6959DEB77D2B8B9926D26F?sequence=1" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/f1/ba/f1bab1ac58865c8cfa5b3c1ca74afdac63173cee.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2312/egs.20081029"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Temporally Coherent General Dynamic Scene Reconstruction [article]

Armin Mustafa, Marco Volino, Hansung Kim, Jean-Yves Guillemaut, Adrian Hilton
<span title="2020-08-03">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This paper introduces a general approach to obtain a 4D representation of complex dynamic scenes from multi-view wide-baseline static or moving cameras without prior knowledge of the scene structure, appearance  ...  Contributions of the work are: An automatic method for initial coarse reconstruction to initialize joint estimation; Sparse-to-dense temporal correspondence integrated with joint multi-view segmentation  ...  automatic reconstruction of general scenes.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1907.08195v2">arXiv:1907.08195v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pcjsowtlj5ejdpnidxerof2kcy">fatcat:pcjsowtlj5ejdpnidxerof2kcy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200805004154/https://arxiv.org/pdf/1907.08195v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1907.08195v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

The video mesh: A data structure for image-based three-dimensional video editing

Jiawen Chen, Sylvain Paris, Jue Wang, Wojciech Matusik, Michael Cohen, Fredo Durand
<span title="">2011</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/klkbknw2u5bm5e3z2bhvy3vfpi" style="color: black;">2011 IEEE International Conference on Computational Photography (ICCP)</a> </i> &nbsp;
The video mesh allows interactive editing of moving objects and modeling of depth, which enables 3D effects and post-exposure camera control.  ...  The video mesh sparsely encodes optical flow as well as depth, and handles occlusion using local layering and alpha mattes. Motion is described by a sparse set of points tracked over time.  ...  Introduction We introduce the video mesh, a new representation that encodes the motion, layering, and 3D structure of a video sequence in a unified data structure.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/iccphot.2011.5753118">doi:10.1109/iccphot.2011.5753118</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/iccp/ChenPWMCD11.html">dblp:conf/iccp/ChenPWMCD11</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/najxm5sysres5d4dl7dz4y3hey">fatcat:najxm5sysres5d4dl7dz4y3hey</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20130615033725/http://research.microsoft.com/en-us/um/people/cohen/videomesh.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e3/e7/e3e78f92ed7a4124be488d3b210eacfe6be2f7dd.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/iccphot.2011.5753118"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Community-driven Generation of 3D and Augmented Web Content for Archaeology [article]

Panagiotis D. Ritsos, Andrew T. Wilson, Helen C. Miles, Lee F. Williams, Bernard Tiddeman, Frédéric Labrosse, Seren Griffiths, Ben Edwards, Katharina Möller, Raimund Karl, Jonathan C. Roberts
<span title="">2014</span> <i title="The Eurographics Association"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/7kytuzv5ebf5vhesssjzlt6bvu" style="color: black;">Eurographics Workshop on Graphics and Cultural Heritage</a> </i> &nbsp;
In this paper, discussing work-in progress, we present our automatic process that takes the user's uploaded photographs, converts them into 3D models and displays them in two presentation platforms - in  ...  a web gallery application, using X3D/X3DOM, and in mobile augmented reality, using awe.js.  ...  Acknowledgments We acknowledge the AHRC (UK) AH/L007916/1 for funding this work, and members of our research team for their continued involvement in this research.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2312/gch.20141321">doi:10.2312/gch.20141321</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/vast/RitsosWMWTLGEMK14.html">dblp:conf/vast/RitsosWMWTLGEMK14</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ps7s6ujhenb5pevccyqr7vgp5m">fatcat:ps7s6ujhenb5pevccyqr7vgp5m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220120013236/https://diglib.eg.org/xmlui/bitstream/handle/10.2312/gch.20141321.025-028/025-028.pdf;jsessionid=E2A1C306D3E82A4A057F3AB1B95678A1?sequence=1" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/c2/07/c207897cc5273bbe68b26051ff20b0278a6c927f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2312/gch.20141321"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

ILabel: Interactive Neural Scene Labelling [article]

Shuaifeng Zhi and Edgar Sucar and Andre Mouton and Iain Haughton and Tristan Laidlow and Andrew J. Davison
<span title="2021-12-03">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Joint representation of geometry, colour and semantics using a 3D neural field enables accurate dense labelling from ultra-sparse interactions as a user reconstructs a scene in real-time using a handheld  ...  A room or similar scene can be accurately labelled into 10+ semantic categories with only a few tens of clicks.  ...  By supervising the network on the sparse annotations, semantics are automatically propagated.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.14637v2">arXiv:2111.14637v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6rklf4bv5bam5gm2iaza5m557m">fatcat:6rklf4bv5bam5gm2iaza5m557m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211207045913/https://arxiv.org/pdf/2111.14637v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/4f/1f/4f1ffa020c0741ea57ad7acd02c9d58be5fa5f20.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.14637v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 2,454 results