Filters








8,312 Hits in 8.6 sec

Pixels, voxels, and views: A study of shape representations for single view 3D object shape prediction [article]

Daeyun Shin, Charless C. Fowlkes, Derek Hoiem
<span title="2018-06-12">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The goal of this paper is to compare surface-based and volumetric 3D object shape representations, as well as viewer-centered and object-centered reference frames for single-view 3D shape prediction.  ...  We propose a new algorithm for predicting depth maps from multiple viewpoints, with a single depth or RGB image as input.  ...  More study is needed in this direction. Conclusion Recent methods to produce 3D shape from a single image have used a variety of representation for shape (voxels, octrees, multiple depth maps).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1804.06032v2">arXiv:1804.06032v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/h3qu4m3afnbgphopq4vzgxdkka">fatcat:h3qu4m3afnbgphopq4vzgxdkka</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200928171020/https://arxiv.org/pdf/1804.06032v2.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/d4/ab/d4ab6ac02ebb9f1252f73dc3ea1b4737fa68f9b1.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1804.06032v2" 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>

Pixels, Voxels, and Views: A Study of Shape Representations for Single View 3D Object Shape Prediction

Daeyun Shin, Charless C. Fowlkes, Derek Hoiem
<span title="">2018</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition</a> </i> &nbsp;
The goal of this paper is to compare surface-based and volumetric 3D object shape representations, as well as viewer-centered and object-centered reference frames for single-view 3D shape prediction.  ...  We propose a new algorithm for predicting depth maps from multiple viewpoints, with a single depth or RGB image as input.  ...  More study is needed in this direction. Conclusion Recent methods to produce 3D shape from a single image have used a variety of representation for shape (voxels, octrees, multiple depth maps).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2018.00323">doi:10.1109/cvpr.2018.00323</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/ShinFH18.html">dblp:conf/cvpr/ShinFH18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nqhebnzh5zfllfo7iggwu2gsqa">fatcat:nqhebnzh5zfllfo7iggwu2gsqa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190819022605/http://openaccess.thecvf.com:80/content_cvpr_2018/papers/Shin_Pixels_Voxels_and_CVPR_2018_paper.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/f8/db/f8db9c2b8cef037c308ad3a280c653c3820a834c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2018.00323"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

PVSeRF: Joint Pixel-, Voxel- and Surface-Aligned Radiance Field for Single-Image Novel View Synthesis [article]

Xianggang Yu, Jiapeng Tang, Yipeng Qin, Chenghong Li, Linchao Bao, Xiaoguang Han, Shuguang Cui
<span title="2022-02-10">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We present PVSeRF, a learning framework that reconstructs neural radiance fields from single-view RGB images, for novel view synthesis.  ...  To address this challenge, we propose to incorporate explicit geometry reasoning and combine it with pixel-aligned features for radiance field prediction.  ...  Single-view 3D Object Reconstruction Given a single image containing a object, 3D object reconstruction aims to recover the 3D geometry of the object.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.04879v1">arXiv:2202.04879v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/iacxkdhstfgrncxr4wxvux4zrm">fatcat:iacxkdhstfgrncxr4wxvux4zrm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220215110026/https://arxiv.org/pdf/2202.04879v1.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/60/89/6089453ba8368c41811d90ec72e07dcc21c549d6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.04879v1" 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>

Multi-view Supervision for Single-View Reconstruction via Differentiable Ray Consistency

Shubham Tulsiani, Tinghui Zhou, Alexei A. Efros, Jitendra Malik
<span title="">2017</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)</a> </i> &nbsp;
for learning single-view 3D prediction.  ...  We study the notion of consistency between a 3D shape and a 2D observation and propose a differentiable formulation which allows computing gradients of the 3D shape given an observation from an arbitrary  ...  We gratefully acknowledge NVIDIA corporation for the donation of Tesla GPUs used for this research.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2017.30">doi:10.1109/cvpr.2017.30</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/TulsianiZEM17.html">dblp:conf/cvpr/TulsianiZEM17</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kvvkkk75ljdj7fbzlwif4ik3na">fatcat:kvvkkk75ljdj7fbzlwif4ik3na</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190819022341/http://openaccess.thecvf.com:80/content_cvpr_2017/papers/Tulsiani_Multi-View_Supervision_for_CVPR_2017_paper.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/ab/8b/ab8bfe4dbcdd6e9514d4adc3ff9af3e116e431b5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2017.30"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistency [article]

Shubham Tulsiani, Tinghui Zhou, Alexei A. Efros, Jitendra Malik
<span title="2017-04-20">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
for learning single-view 3D prediction.  ...  We study the notion of consistency between a 3D shape and a 2D observation and propose a differentiable formulation which allows computing gradients of the 3D shape given an observation from an arbitrary  ...  We gratefully acknowledge NVIDIA corporation for the donation of Tesla GPUs used for this research.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1704.06254v1">arXiv:1704.06254v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xmzflirmizdx7a5iq62yq75k2m">fatcat:xmzflirmizdx7a5iq62yq75k2m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200826100632/https://arxiv.org/pdf/1704.06254v1.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/ae/58/ae587a4a8842fbe01b9a043b66f762a89dca5074.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1704.06254v1" 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>

Learning View Priors for Single-view 3D Reconstruction [article]

Hiroharu Kato, Tatsuya Harada
<span title="2019-03-29">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Because of this ambiguity, although a 3D object reconstructor can be trained using a single view or a few views per object, reconstructed shapes only fit the observed views and appear incorrect from the  ...  There is some ambiguity in the 3D shape of an object when the number of observed views is small.  ...  Acknowledgment This work was partially funded by ImPACT Program of Council for Science, Technology and Innovation (Cabinet Office, Government of Japan) and partially supported by JST CREST Grant Number  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1811.10719v2">arXiv:1811.10719v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3jnpm3zalbg7la5ples34fgw4a">fatcat:3jnpm3zalbg7la5ples34fgw4a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191019054751/https://arxiv.org/pdf/1811.10719v2.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/e7/12/e712a5e4d83e1d3a3e9d2d8f67c6612e7b40eca1.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1811.10719v2" 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>

3D Shape Reconstruction from Sketches via Multi-view Convolutional Networks [article]

Zhaoliang Lun, Matheus Gadelha, Evangelos Kalogerakis, Subhransu Maji, Rui Wang
<span title="2017-09-29">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We propose a method for reconstructing 3D shapes from 2D sketches in the form of line drawings.  ...  Our method takes as input a single sketch, or multiple sketches, and outputs a dense point cloud representing a 3D reconstruction of the input sketch(es).  ...  We acknowledge the MassTech Collaborative grant for funding the UMass GPU cluster.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1707.06375v3">arXiv:1707.06375v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pphspwefmrbuxjlvnd7bxy75tu">fatcat:pphspwefmrbuxjlvnd7bxy75tu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191017163847/https://arxiv.org/pdf/1707.06375v3.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/97/65/9765c370796001d4030cc1ed6139ba159bca7c6e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1707.06375v3" 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>

Multi-View Silhouette and Depth Decomposition for High Resolution 3D Object Representation [article]

Edward Smith, Scott Fujimoto, David Meger
<span title="2018-11-14">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Drawing motivation from the canonical view representation of objects, we introduce a novel method for the fast up-sampling of 3D objects in voxel space through networks that perform super-resolution on  ...  We evaluate our work on multiple experiments concerning high-resolution 3D objects, and show our system is capable of accurately predicting novel objects at resolutions as large as 512×512×512 -- the highest  ...  This decoder receives a latent representation of the 3D shape and produces a probability for occupancy at each discrete position in 3D voxel space.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1802.09987v3">arXiv:1802.09987v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qj27gfxsxnawrozxhfk77beada">fatcat:qj27gfxsxnawrozxhfk77beada</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200902125551/https://arxiv.org/pdf/1802.09987v3.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/19/61/19617cce82360449a0903bf2869d29d8debab416.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1802.09987v3" 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>

ShapeCodes: Self-Supervised Feature Learning by Lifting Views to Viewgrids [article]

Dinesh Jayaraman, Ruohan Gao, Kristen Grauman
<span title="2018-07-31">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We introduce an unsupervised feature learning approach that embeds 3D shape information into a single-view image representation.  ...  The main idea is a self-supervised training objective that, given only a single 2D image, requires all unseen views of the object to be predictable from learned features.  ...  In short, the function of the encoder is to lift a 2D view to a single vector representation of the full 3D object shape.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1709.00505v4">arXiv:1709.00505v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ccyklhukyfhfboqssezau26uzi">fatcat:ccyklhukyfhfboqssezau26uzi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200925005352/https://arxiv.org/pdf/1709.00505v4.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/3a/58/3a587dff43b75263b28e9df56984e20159fe2e10.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1709.00505v4" 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>

MeshMVS: Multi-View Stereo Guided Mesh Reconstruction [article]

Rakesh Shrestha, Zhiwen Fan, Qingkun Su, Zuozhuo Dai, Siyu Zhu, Ping Tan
<span title="2021-04-11">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
First, our system predicts a coarse 3D volume from the color images by probabilistically merging voxel occupancy grids from the prediction of individual views.  ...  Deep learning based 3D shape generation methods generally utilize latent features extracted from color images to encode the semantics of objects and guide the shape generation process.  ...  Our system can struggle to roughly reconstruct shapes with very complex topology while some fine topology of the mesh is missing.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.08682v3">arXiv:2010.08682v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mszoiznjofcqllyc77ywdkqogu">fatcat:mszoiznjofcqllyc77ywdkqogu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210414185908/https://arxiv.org/pdf/2010.08682v3.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/75/a8/75a8800112b3ffdaff38110c5b38e779e5325687.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.08682v3" 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>

Learning a Multi-View Stereo Machine [article]

Abhishek Kar, Christian Häne, Jitendra Malik
<span title="2017-08-17">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In contrast to recent learning based methods for 3D reconstruction, we leverage the underlying 3D geometry of the problem through feature projection and unprojection along viewing rays.  ...  We present a learnt system for multi-view stereopsis.  ...  The authors would like to thank David Fouhey, Saurabh Gupta and Shubham Tulsiani for valuable discussions and Fyusion Inc. for providing GPU hours for the work.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1708.05375v1">arXiv:1708.05375v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/o5ism2lpmrabfmpxa5k7ecgfjq">fatcat:o5ism2lpmrabfmpxa5k7ecgfjq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200929093233/https://arxiv.org/pdf/1708.05375v1.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/db/c0/dbc04b17de3ba67a0a3382cc3128ba513491670a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1708.05375v1" 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>

Conditional Single-view Shape Generation for Multi-view Stereo Reconstruction [article]

Yi Wei, Shaohui Liu, Wang Zhao, Jiwen Lu, Jie Zhou
<span title="2019-04-21">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Then, we formulate the task of multi-view reconstruction as taking the intersection of the predicted shape spaces on each single image.  ...  Experimental results and ablation studies show that our proposed approach outperforms state-of-the-art methods on 3D reconstruction test error and demonstrate its generalization ability on real world data  ...  Acknowledgements This work was supported in part by the National Natural Science Foundation of China under Grant U1813218, Grant 61822603, Grant U1713214, Grant 61672306, and Grant 61572271.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.06699v2">arXiv:1904.06699v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/khnrizpp6vdqloidfnweyrsjwy">fatcat:khnrizpp6vdqloidfnweyrsjwy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200826160039/https://arxiv.org/pdf/1904.06699v2.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/1b/12/1b12dfa8a5789c0c5305d95d459e23df32040da1.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.06699v2" 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>

Multi-view to Novel View: Synthesizing Novel Views With Self-learned Confidence [chapter]

Shao-Hua Sun, Minyoung Huh, Yuan-Hong Liao, Ning Zhang, Joseph J. Lim
<span title="">2018</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
Specifically, our model consists of a flow prediction module and a pixel generation module to directly leverage information presented in source views as well as hallucinate missing pixels from statistical  ...  We evaluate our model on images rendered from 3D object models as well as real and synthesized scenes.  ...  Acknowledgments This project was supported by the center for super intelligence, Kakao Brain, and SKT. This research of Shao-Hua Sun and Minyoung Huh were partially supported by Snap Inc.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-01219-9_10">doi:10.1007/978-3-030-01219-9_10</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/x54uve2m4zdnrgcvlnczfjp67i">fatcat:x54uve2m4zdnrgcvlnczfjp67i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190728160114/http://openaccess.thecvf.com:80/content_ECCV_2018/papers/Shao-Hua_Sun_Multi-view_to_Novel_ECCV_2018_paper.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/39/4b/394bf41cd8578ec10cd34452c688c3e3de1c16a7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-01219-9_10"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Multi-view Consistency as Supervisory Signal for Learning Shape and Pose Prediction [article]

Shubham Tulsiani, Alexei A. Efros, Jitendra Malik
<span title="2018-04-24">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We present a framework for learning single-view shape and pose prediction without using direct supervision for either.  ...  Our proposed training setup enforces geometric consistency between the independently predicted shape and pose from two views of the same instance.  ...  This work was supported in part by Intel/NSF VEC award IIS-1539099 and NSF Award IIS-1212798. We gratefully acknowledge NVIDIA corporation for the donation of GPUs used for this research.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1801.03910v2">arXiv:1801.03910v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fj7s4amks5g75feh7ky7356aza">fatcat:fj7s4amks5g75feh7ky7356aza</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200930211707/https://arxiv.org/pdf/1801.03910v2.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/2a/85/2a85651830e51ffe9d0ed67116e582e22b859fa5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1801.03910v2" 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>

3D Sketching using Multi-View Deep Volumetric Prediction

Johanna Delanoy, Mathieu Aubry, Phillip Isola, Alexei A. Efros, Adrien Bousseau
<span title="2018-07-25">2018</span> <i title="Association for Computing Machinery (ACM)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/vwuvhyu5afandlw5zzpfw7slo4" style="color: black;">Proceedings of the ACM on Computer Graphics and Interactive Techniques</a> </i> &nbsp;
We complement this single-view network with an updater CNN that refines an existing prediction given a new drawing of the shape created from a novel viewpoint.  ...  At the core of our approach is a deep convolutional neural network (CNN) that predicts occupancy of a voxel grid from a line drawing.  ...  ACKNOWLEDGMENTS Many thanks to Yulia Gryaditskaya for sketching several of our results, and for her help on the renderings and video.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3203197">doi:10.1145/3203197</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/journals/pacmcgit/DelanoyAIEB18.html">dblp:journals/pacmcgit/DelanoyAIEB18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vwt4h6uo5rgejae42wo4s6nqga">fatcat:vwt4h6uo5rgejae42wo4s6nqga</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190501172627/https://hal.inria.fr/hal-01799600/document" 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/44/7e/447eaf666fe95441bfb55ff10f5dd5b7ad2830ca.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3203197"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 8,312 results