Deep 3D reconstruction: methods, data, and challenges

Caixia LIU; Dehui KONG; Shaofan WANG; Zhiyong WANG; Jinghua LI; Baocai YIN

doi:10.1631/FITEE.2000068

Your Location：

Home >

Browse articles >

Deep 3D reconstruction: methods, data, and challenges

Regular Papers | Updated：2022-05-19

- Deep 3D reconstruction: methods, data, and challenges
- 深度三维重建：方法、数据和挑战
- Frontiers of Information Technology & Electronic Engineering Vol. 22, Issue 5, Pages: 652-672(2021)
- Affiliations：
  
  Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China
  Multimedia Laboratory, School of Computer Science, University of Sydney, Sydney NSW 2006, Australia
- Author bio：
  
  [ "Caixia LIU, E-mail: lcxxib@emails.bjut.edu.cn" ]
  Shaofan WANG, E-mail: wangshaofan@bjut.edu.cn
- Funds：
- DOI：10.1631/FITEE.2000068
  CLC： TP391
- Received：11 February 2020，
  
  Revised：2020-12-29，
  
  Published：2021-05
- Accepted：
Scan QR Code
Caixia LIU, Dehui KONG, Shaofan WANG, et al. Deep 3D reconstruction: methods, data, and challenges[J]. Frontiers of Information Technology & Electronic Engineering, 2021, 22(5): 652-672.
DOI：

Caixia LIU, Dehui KONG, Shaofan WANG, et al. Deep 3D reconstruction: methods, data, and challenges[J]. Frontiers of Information Technology & Electronic Engineering, 2021, 22(5): 652-672. DOI： 10.1631/FITEE.2000068.

摘要

三维形状重建是计算机视觉、计算机图形学、模式识别和虚拟现实等领域的重要研究课题。现有三维重建方法通常存在两个瓶颈：（1）它们涉及多个人工设计阶段，导致累积误差，且难以自动学习三维形状的语义特征；（2）它们严重依赖图像内容和质量，以及精确校准的摄像机。因此，这些方法的重建精度难以提高。基于深度学习的三维重建方法通过利用深度网络自动学习低质量图像中的三维形状语义特征，克服了这两个瓶颈。然而，这些方法具有多种体系框架，但是至今未有文献对它们作深入分析和比较。本文对基于深度学习的三维重建方法进行全面综述。首先，基于不同深度学习模型框架，将基于深度学习的三维重建方法分为4类：递归神经网络、深自编码器、生成对抗网络和卷积神经网络，并对相应方法作详细分析。其次，详细介绍上述方法常用的4个代表性数据库。再次，对基于深度学习的三维重建方法进行综合比较，包括不同方法在同一数据库、同一方法在不同数据库以及同一方法对于不同视角个数输入的结果比较。最后，讨论了基于深度学习的三维重建方法的发展趋势。

Abstract

Three-dimensional (3D) reconstruction of shapes is an important research topic in the fields of computer vision

computer graphics

pattern recognition

and virtual reality. Existing 3D reconstruction methods usually suffer from two bottlenecks: (1) they involve multiple manually designed states which can lead to cumulative errors

but can hardly learn semantic features of 3D shapes automatically; (2) they depend heavily on the content and quality of images

as well as precisely calibrated cameras. As a result

it is difficult to improve the reconstruction accuracy of those methods. 3D reconstruction methods based on deep learning overcome both of these bottlenecks by automatically learning semantic features of 3D shapes from low-quality images using deep networks. However

while these methods have various architectures

in-depth analysis and comparisons of them are unavailable so far. We present a comprehensive survey of 3D reconstruction methods based on deep learning. First

based on different deep learning model architectures

we divide 3D reconstruction methods based on deep learning into four types

recurrent neural network

deep autoencoder

generative adversarial network

and convolutional neural network based methods

and analyze the corresponding methodologies carefully. Second

we investigate four representative databases that are commonly used by the above methods in detail. Third

we give a comprehensive comparison of 3D reconstruction methods based on deep learning

which consists of the results of different methods with respect to the same database

the results of each method with respect to different databases

and the robustness of each method with respect to the number of views. Finally

we discuss future development of 3D reconstruction methods based on deep learning.

关键词

Keywords

references

S Agarwal , , , N Snavely , , , I Simon , , , 等 . . Building Rome in a day . . IEEE 12 th Int Conf on Computer Vision , , 2009 . . p.72 - - 79 . . DOI: 10.1109/ICCV.2009.5459148 http://doi.org/10.1109/ICCV.2009.5459148 . .

I Akhter , , , MJ Black . . Pose-conditioned joint angle limits for 3D human pose reconstruction . . IEEE Conf on Computer Vision and Pattern Recognition , , 2015 . . p. 1446 - - 1455 . . DOI: 10.1109/CVPR.2015.7298751 http://doi.org/10.1109/CVPR.2015.7298751 . .

A Bansal , , , B Russell , , , A Gupta . . Marr revisited: 2D-3D alignment via surface normal prediction . . IEEE Conf on Computer Vision and Pattern Recognition , , 2016 . . p. 5965 - - 5974 . . DOI: 10.1109/CVPR.2016.642 http://doi.org/10.1109/CVPR.2016.642 . .

J Bruna , , , W Zaremba , , , A Szlam , , , 等 . . Spectral networks and locally connected networks on graphs . . Int Conf on Learning Representations , , 2013 . . p. 1 - - 14 . . . .

F Calakli , , , G Taubin . . SSD: smooth signed distance surface reconstruction . . Comput Graph Forum , , 2011 . . 30 ( ( 7 ): ): 1993 - - 2002 . . DOI: 10.1111/j.1467-8659.2011.02058.x http://doi.org/10.1111/j.1467-8659.2011.02058.x . .

YP Cao , , , ZN Liu , , , ZF Kuang , , , 等 . . Learning to reconstruct high-quality 3D shapes with cascaded fully convolutional networks . . Proc 15 th European Conf on Computer Vision , , 2018 . . p. 616 - - 633 . . DOI: 10.1007/978-3-030-01240-3_38 http://doi.org/10.1007/978-3-030-01240-3_38 . .

AX Chang , , , T Funkhouser , , , L Guibas , , , 等 . . ShapeNet: an information-rich 3D model repository . . 2015 . . https://arxiv.org/abs/1512.03012 https://arxiv.org/abs/1512.03012 , , . .

K Chen , , , YK Lai , , , SM Hu . . 3D indoor scene modeling from RGB-D data: a survey . . Comput Vis Media , , 2015 . . 1 ( ( 4 ): ): 267 - - 278 . . DOI: 10.1007/s41095-015-0029-x http://doi.org/10.1007/s41095-015-0029-x . .

CB Choy , , , DF Xu , , , J Gwak , , , 等 . . 3D-R2N2: a unified approach for single and multi-view 3D object reconstruction . . Proc 14 th European Conf on Computer Vision , , 2016 . . p. 628 - - 644 . . DOI: 10.1007/978-3-319-46484-8_38 http://doi.org/10.1007/978-3-319-46484-8_38 . .

TS Cohen , , , M Welling . . Group equivariant convolutional networks . . Proc 33 rd Int Conf on Machine Learning , , 2016 . . p. 2990 - - 2999 . . . .

TS Cohen , , , M Geiger , , , J Köhler , , , 等 . . Spherical CNNs . . Int Conf on Learning Representations , , 2018 . . p.1 - - 15 . . . .

A Dai , , , CR Qi , , , M Nießner . . Shape completion using 3D-encoder-predictor CNNs and shape synthesis . . IEEE Conf on Computer Vision and Pattern Recognition , , 2017 . . p.6545 - - 6554 . . DOI: 10.1109/CVPR.2017.693 http://doi.org/10.1109/CVPR.2017.693 . .

E Denton , , , S Chintala , , , A Szlam , , , 等 . . Deep generative image models using a Laplacian pyramid of adversarial networks . . Proc 28 th Int Conf on Neural Information Processing Systems , , 2015 . . p. 1486 - - 1494 . . . .

J Engel , , , T Schöps , , , D Cremers . . LSD-SLAM: large-scale direct monocular SLAM . . Proc 13 th European Conf on Computer Vision , , 2014 . . p.834 - - 849 . . DOI: 10.1007/978-3-319-10605-2_54 http://doi.org/10.1007/978-3-319-10605-2_54 . .

M Everingham , , , SMA Eslami , , , L van Gool , , , 等 . . The PASCAL visual object classes challenge: a retrospective . . Int J Comput Vis , , 2015 . . 111 ( ( 1 ): ): 98 - - 136 . . DOI: 10.1007/s11263-014-0733-5 http://doi.org/10.1007/s11263-014-0733-5 . .

HQ Fan , , , H Su , , , L Guibas . . A point set generation network for 3D object reconstruction from a single image . . IEEE Conf on Computer Vision and Pattern Recognition , , 2017 . . p. 2463 - - 2471 . . DOI: 10.1109/CVPR.2017.264 http://doi.org/10.1109/CVPR.2017.264 . .

A Fitzgibbon , , , A Zisserman . . Automatic 3D model acquisition and generation of new images from video sequences . . Proc 9 th European Signal Processing Conf , , 1998 . . p. 129 - - 140 . . . .

Y Furukawa , , , J Ponce . . Carved visual hulls for image-based modeling . . Proc 9 th European Conf on Computer Vision , , 2006 . . p.564 - - 577 . . DOI: 10.1007/11744023_44 http://doi.org/10.1007/11744023_44 . .

M Gadelha , , , S Maji , , , R Wang . . 3D shape induction from 2D views of multiple objects . . Int Conf on 3D Vision , , 2017 . . p. 402 - - 411 . . DOI: 10.1109/3DV.2017.00053 http://doi.org/10.1109/3DV.2017.00053 . .

R Girdhar , , , DF Fouhey , , , M Rodriguez , , , 等 . . Learning a predictable and generative vector representation for objects . . Proc 14 th European Conf on Computer Vision , , 2016 . . p. 484 - - 499 . . DOI: 10.1007/978-3-319-46466-4_29 http://doi.org/10.1007/978-3-319-46466-4_29 . .

M Goesele , , , N Snavely , , , B Curless , , , 等 . . Multi-view stereo for community photo collections . . IEEE 11 th Int Conf on Computer Vision , , 2007 . . p. 1 - - 8 . . DOI: 10.1109/ICCV.2007.4408933 http://doi.org/10.1109/ICCV.2007.4408933 . .

I Goodfellow . . NIPS tutorial: generative adversarial networks . . 2016 . . https://arxiv.org/abs/1701.00160 https://arxiv.org/abs/1701.00160 , , . .

IJ Goodfellow , , , J Pouget-Abadie , , , M Mirza , , , 等 . . Generative adversarial nets . . Proc 27 th Int Conf on Neural Information Processing Systems , , 2014 . . p. 2672 - - 2680 . . . .

B Graham . . Spatially-sparse convolutional neural networks . . 2014 . . https://arxiv.org/abs/1409.6070v1 https://arxiv.org/abs/1409.6070v1 , , . .

B Graham . . Sparse 3D convolutional neural networks . . Proc British Machine Vision Conf , , 2015 . . p. 150.1 - - 150.9 . . DOI: 10.5244/C.29.150 http://doi.org/10.5244/C.29.150 . .

K Gregor , , , I Danihelka , , , A Graves , , , 等 . . DRAW: a recurrent neural network for image generation . . Proc 32 nd Int Conf on Machine Learning , , 2015 . . p. 1462 - - 1471 . . . .

I Gulrajani , , , F Ahmed , , , M Arjovsky , , , 等 . . Improved training of Wasserstein GANs . . Advances in Neural Information Processing Systems , , 2017 . . p.5767 - - 5777 . . . .

J Gwak , , , CB Choy , , , M Chandraker , , , 等 . . Weakly supervised 3D reconstruction with adversarial constraint . . Int Conf on 3D Vision , , 2017 . . p.263 - - 272 . . DOI: 10.1109/3DV.2017.00038 http://doi.org/10.1109/3DV.2017.00038 . .

XF Han , , , H Laga , , , M Bennamoun . . Image-based 3D object reconstruction: state-of-the-art and trends in the deep learning era . . IEEE Trans Patt Anal Mach Intell , , 2019 . . 43 ( ( 5 ): ): 1578 - - 1604 . . DOI: 10.1109/TPAMI.2019.2954885 http://doi.org/10.1109/TPAMI.2019.2954885 . .

XG Han , , , Z Li , , , HB Huang , , , 等 . . High-resolution shape completion using deep neural networks for global structure and local geometry inference . . IEEE Int Conf on Computer Vision , , 2017 . . p. 85 - - 93 . . DOI: 10.1109/ICCV.2017.19 http://doi.org/10.1109/ICCV.2017.19 . .

C Häne , , , S Tulsiani , , , J Malik . . Hierarchical surface prediction for 3D object reconstruction . . Int Conf on 3D Vision , , 2017 . . p. 412 - - 420 . . DOI: 10.1109/3DV.2017.00054 http://doi.org/10.1109/3DV.2017.00054 . .

P Henderson , , , V Ferrari . . Learning single-image 3D reconstruction by generative modelling of shape, pose and shading . . Int J Comput Vis , , 2019 . . 128 835 - - 854 . . DOI: 10.1007/s11263-019-01219-8 http://doi.org/10.1007/s11263-019-01219-8 . .

S Hochreiter , , , J Schmidhuber . . Long short-term memory . . Neur Comput , , 1997 . . 9 ( ( 8 ): ): 1735 - - 1780 . . DOI: 10.1162/neco.1997.9.8.1735 http://doi.org/10.1162/neco.1997.9.8.1735 . .

WZ Hu , , , SC Zhu . . Learning 3D object templates by quantizing geometry and appearance spaces . . IEEE Trans Patt Anal Mach Intell , , 2015 . . 37 ( ( 6 ): ): 1190 - - 1205 . . DOI: 10.1109/TPAMI.2014.2362141 http://doi.org/10.1109/TPAMI.2014.2362141 . .

QX Huang , , , H Wang , , , V Koltun . . Single-view reconstruction via joint analysis of image and shape collections . . ACM Trans Graph , , 2015 . . 34 ( ( 4 ): ): 87 DOI: 10.1145/2766890 http://doi.org/10.1145/2766890 . .

TN Kipf , , , M Welling . . Semi-supervised classification with graph convolutional networks . . Int Conf on Learning Representations , , 2017 . . p. 1 - - 13 . . . .

C Kong , , , CH Lin , , , S Lucey . . Using locally corresponding CAD models for dense 3D reconstructions from a single image . . IEEE Conf on Computer Vision and Pattern Recognition , , 2017 . . p.5603 - - 5611 . . DOI: 10.1109/CVPR.2017.594 http://doi.org/10.1109/CVPR.2017.594 . .

A Krizhevsky , , , I Sutskever , , , GE Hinton . . ImageNet classification with deep convolutional neural networks . . Proc 25 th Int Conf on Neural Information Processing Systems , , 2012 . . p. 1 - - 9 . . . .

H Laga . . A survey on deep learning architectures for image-based depth reconstruction . . 2019 . . https://arxiv.org/abs/1906.06113 https://arxiv.org/abs/1906.06113 , , . .

M Lhuillier , , , L Quan . . A quasi-dense approach to surface reconstruction from uncalibrated images . . IEEE Trans Patt Anal Mach Intell , , 2005 . . 27 ( ( 3 ): ): 418 - - 433 . . DOI: 10.1109/TPAMI.2005.44 http://doi.org/10.1109/TPAMI.2005.44 . .

C Li , , , M Wand . . Precomputed real-time texture synthesis with Markovian generative adversarial networks . . Proc 14 th European Conf on Computer Vision , , 2016 . . p. 702 - - 716 . . DOI: 10.1007/978-3-319-46487-9_43 http://doi.org/10.1007/978-3-319-46487-9_43 . .

YY Li , , , A Dai , , , L Guibas , , , 等 . . Database-assisted object retrieval for real-time 3D reconstruction . . Comput Graph Forum , , 2015 . . 34 ( ( 2 ): ): 435 - - 446 . . DOI: 10.1111/cgf.12573 http://doi.org/10.1111/cgf.12573 . .

JJ Lim , , , H Pirsiavash , , , A Torralba . . Parsing IKEA objects: fine pose estimation . . IEEE Int Conf on Computer Vision , , 2014 . . p. 2992 - - 2999 . . DOI: 10.1109/ICCV.2013.372 http://doi.org/10.1109/ICCV.2013.372 . .

CH Lin , , , C Kong , , , S Lucey . . Learning efficient point cloud generation for dense 3D object reconstruction . . AAAI Conf on Artificial Intelligence , , 2018 . . p. 7114 - - 7121 . . . .

SC Liu , , , WK Chen , , , TY Li , , , 等 . . Soft rasterizer: differentiable rendering for unsupervised single-view mesh reconstruction . . 2019 . . https://arxiv.org/abs/1901.05567v1 https://arxiv.org/abs/1901.05567v1 , , . .

ZL Lun , , , M Gadelha , , , E Kalogerakis , , , 等 . . 3D shape reconstruction from sketches via multi-view convolutional networks . . Int Conf on 3D Vision , , 2017 . . p. 67 - - 77 . . DOI: 10.1109/3DV.2017.00018 http://doi.org/10.1109/3DV.2017.00018 . .

LL Nan , , , K Xie , , , A Sharf . . A search-classify approach for cluttered indoor scene understanding . . ACM Trans Graph , , 2012 . . 31 ( ( 6 ): ): 137.1 - - 137.10 . . DOI: 10.1145/2366145.2366156 http://doi.org/10.1145/2366145.2366156 . .

C Nash , , , CKI Williams . . The shape variational autoencoder: a deep generative model of part-segmented 3D objects . . Comput Graph Forum , , 2017 . . 36 ( ( 5 ): ): 1 - - 12 . . DOI: 10.1111/cgf.13240 http://doi.org/10.1111/cgf.13240 . .

A Newell , , , KY Yang , , , J Deng . . Stacked hourglass networks for human pose estimation . . Proc 14 th European Conf on Computer Vision , , 2016 . . p. 483 - - 499 . . DOI: 10.1007/978-3-319-46484-8_29 http://doi.org/10.1007/978-3-319-46484-8_29 . .

CJ Niu , , , J Li , , , K Xu . . Im2Struct: recovering 3D shape structure from a single RGB image . . IEEE/CVF Conf on Computer Vision and Pattern Recognition , , 2018 . . p. 1 - - 9 . . DOI: 10.1109/CVPR.2018.00475 http://doi.org/10.1109/CVPR.2018.00475 . .

JK Pontes , , , C Kong , , , A Eriksson , , , 等 . . Compact model representation for 3D reconstruction . . Int Conf on 3D Vision , , 2017 . . p. 88 - - 96 . . DOI: 10.1109/3DV.2017.00020 http://doi.org/10.1109/3DV.2017.00020 . .

JK Pontes , , , C Kong , , , S Sridharan , , , 等 . . Image2Mesh: a learning framework for single image 3D reconstruction . . Proc 14 th Asian Conf on Computer Vision , , 2018 . . p. 365 - - 381 . . DOI: 10.1007/978-3-030-20887-5_23 http://doi.org/10.1007/978-3-030-20887-5_23 . .

A Radford , , , L Metz , , , S Chintala . . Unsupervised representation learning with deep convolutional generative adversarial networks . . Int Conf on Learning Representations , , 2015 . . p. 1 - - 16 . . . .

DJ Rezende , , , SMA Eslami , , , S Mohamed , , , 等 . . Unsupervised learning of 3D structure from images . . Proc 30 th Conf on Neural Information Processing Systems , , 2016 . . p.4997 - - 5005 . . . .

TJ Shao , , , WW Xu , , , K Zhou , , , 等 . . An interactive approach to semantic modeling of indoor scenes with an RGBD camera . . ACM Trans Graph , , 2012 . . 31 ( ( 6 ): ): 136 DOI: 10.1145/2366145.2366155 http://doi.org/10.1145/2366145.2366155 . .

YF Shi , , , PX Long , , , K Xu , , , 等 . . Data-driven contextual modeling for 3D scene understanding . . Comput Graph , , 2016 . . 55 55 - - 67 . . DOI: 10.1016/j.cag.2015.11.003 http://doi.org/10.1016/j.cag.2015.11.003 . .

N Silberman , , , D Hoiem , , , P Kohli , , , 等 . . Indoor segmentation and support inference from RGBD images . . Proc 12 th European Conf on Computer Vision , , 2012 . . p. 746 - - 760 . . DOI: 10.1007/978-3-642-33715-4_54 http://doi.org/10.1007/978-3-642-33715-4_54 . .

K Simonyan , , , A Zisserman . . Very deep convolutional networks for large-scale image recognitions . . Int Conf on Learning Representations , , 2015 . . p. 1 - - 14 . . . .

EJ Smith , , , D Meger . . Improved adversarial systems for 3D object generation and reconstruction . . Proc 1 st Annual Conf on Robot Learning , , 2017 . . p.87 - - 96 . . . .

XY Sun , , , JJ Wu , , , XM Zhang , , , 等 . . Pix3D: dataset and methods for single-image 3D shape modeling . . IEEE/CVF Conf on Computer Vision and Pattern Recognition , , 2018 . . p.2974 - - 2983 . . DOI: 10.1109/CVPR.2018.00314 http://doi.org/10.1109/CVPR.2018.00314 . .

YY Sun . . A survey of 3D reconstruction based on single image . . J North China Univ Technol , , 2011 . . 23 ( ( 1 ): ): 9 - - 13 . . DOI: 10.3969/j.issn.1001-5477.2011.01.002 http://doi.org/10.3969/j.issn.1001-5477.2011.01.002 . .

M Sundermeyer , , , R Schlüter , , , H Ney . . LSTM neural networks for language modeling . . 2012 . . https://core.ac.uk/display/22066040 https://core.ac.uk/display/22066040 , , . .

I Sutskever , , , O Vinyals , , , Q Le . . Sequence to sequence learning with neural networks . . Proc 27 th Int Conf on Neural Information Processing Systems , , 2014 . . p. 3104 - - 3112 . . . .

M Tatarchenko , , , A Dosovitskiy , , , T Brox . . Octree generating networks: efficient convolutional architectures for high-resolution 3D outputs . . IEEE Int Conf on Computer Vision , , 2017 . . p.2107 - - 2115 . . DOI: 10.1109/ICCV.2017.230 http://doi.org/10.1109/ICCV.2017.230 . .

JD Udayan , , , H Kim , , , JI Kim . . An image-based approach to the reconstruction of ancient architectures by extracting and arranging 3D spatial components . . Front Inform Technol Electron Eng , , 2015 . . 16 ( ( 1 ): ): 12 - - 27 . . DOI: 10.1631/FITEE.1400141 http://doi.org/10.1631/FITEE.1400141 . .

J Varley , , , C DeChant , , , A Richardson , , , 等 . . Shape completion enabled robotic grasping . . IEEE/RSJ Int Conf on Intelligent Robots and Systems , , 2017 . . p. 2442 - - 2447 . . DOI: 10.1109/IROS.2017.8206060 http://doi.org/10.1109/IROS.2017.8206060 . .

LJ Wang , , , Y Fang . . Unsupervised 3D reconstruction from a single image via adversarial learning . . 2017 . . https://arxiv.org/abs/1711.09312 https://arxiv.org/abs/1711.09312 , , . .

NY Wang , , , YD Zhang , , , ZW Li , , , 等 . . Pixel2Mesh: generating 3D mesh models from single RGB images . . Proc 15 th European Conf on Computer Vision , , 2018 . . p. 55 - - 71 . . DOI: 10.1007/978-3-030-01252-6_4 http://doi.org/10.1007/978-3-030-01252-6_4 . .

XL Wang , , , A Gupta . . Generative image modeling using style and structure adversarial networks . . Proc 14 th European Conf on Computer Vision , , 2016 . . p. 318 - - 335 . . DOI: 10.1007/978-3-319-46493-0_20 http://doi.org/10.1007/978-3-319-46493-0_20 . .

JJ Wu , , , CK Zhang , , , TF Xue , , , 等 . . Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling . . Advances in Neural Information Processing Systems , , 2016a . . p. 82 - - 90 . . . .

JJ Wu , , , TF Xue , , , JJ Lim , , , 等 . . Single image 3D interpreter network . . Proc 14 th European Conf on Computer Vision , , 2016b . . p.365 - - 382 . . DOI: 10.1007/978-3-319-46466-4_22 http://doi.org/10.1007/978-3-319-46466-4_22 . .

JJ Wu , , , YF Wang , , , TF Xue , , , 等 . . MarrNet: 3D shape reconstruction via 2.5D sketches . . Advances in Neural Information Processing Systems , , 2017 . . p. 540 - - 550 . . . .

ZR Wu , , , SR Song , , , A Khosla , , , 等 . . 3D ShapeNets: a deep representation for volumetric shapes . . IEEE Conf on Computer Vision and Pattern Recognition , , 2015 . . p.1912 - - 1920 . . DOI: 10.1109/CVPR.2015.7298801 http://doi.org/10.1109/CVPR.2015.7298801 . .

Y Xiang , , , R Mottaghi , , , S Savarese . . Beyond PASCAL: a benchmark for 3D object detection in the wild . . IEEE Winter Conf on Applications of Computer Vision , , 2014 . . p. 75 - - 82 . . DOI: 10.1109/WACV.2014.6836101 http://doi.org/10.1109/WACV.2014.6836101 . .

Y Xiang , , , W Kim , , , W Chen , , , 等 . . ObjectNet3D: a large scale database for 3D object recognition . . Proc 14 th European Conf on Computer Vision , , 2016 . . p. 160 - - 176 . . DOI: 10.1007/978-3-319-46484-8_10 http://doi.org/10.1007/978-3-319-46484-8_10 . .

JX Xiao , , , J Hays , , , KA Ehinger , , , 等 . . SUN database: large-scale scene recognition from abbey to zoo . . IEEE Computer Society Conf on Computer Vision and Pattern Recognition , , 2010 . . p. 3485 - - 3492 . . DOI: 10.1109/CVPR.2010.5539970 http://doi.org/10.1109/CVPR.2010.5539970 . .

HZ Xie , , , HX Yao , , , XS Sun , , , 等 . . Pix2Vox: context-aware 3D reconstruction from single and multi-view images . . IEEE/CVF Int Conf on Computer Vision , , 2019 . . p. 1 - - 9 . . DOI: 10.1109/ICCV.2019.00278 http://doi.org/10.1109/ICCV.2019.00278 . .

XC Yan , , , JM Yang , , , E Yumer , , , 等 . . Perspective transformer nets: learning single-view 3D object reconstruction without 3D supervision . . Advances in Neural Information Processing Systems , , 2016 . . p. 1696 - - 1704 . . . .

B Yang , , , HK Wen , , , S Wang , , , 等 . . 3D object reconstruction from a single depth view with adversarial learning . . IEEE Int Conf on Computer Vision Workshop , , 2018 . . p.679 - - 688 . . DOI: 10.1109/ICCVW.2017.86 http://doi.org/10.1109/ICCVW.2017.86 . .

B Yang , , , S Rosa , , , A Markham , , , 等 . . 3D object dense reconstruction from a single depth view . . IEEE Trans Patt Anal Mach Intell , , 2019 . . 41 ( ( 12 ): ): 2820 - - 2834 . . DOI: 10.1109/TPAMI.2018.2868195 http://doi.org/10.1109/TPAMI.2018.2868195 . .

B Yang , , , S Wang , , , A Markham , , , 等 . . Robust attentional aggregation of deep feature sets for multi-view 3D reconstruction . . Int J Comput Vis , , 2020 . . 128 53 - - 73 . . DOI: 10.1007/s11263-019-01217-w http://doi.org/10.1007/s11263-019-01217-w . .

MD Zeiler , , , D Krishnan , , , GW Taylor , , , 等 . . Deconvolutional networks . . IEEE Computer Society Conf on Computer Vision and Pattern Recognition , , 2010 . . p.2528 - - 2535 . . DOI: 10.1109/CVPR.2010.5539957 http://doi.org/10.1109/CVPR.2010.5539957 . .

CY Zhu , , , RH Byrd , , , PH Lu , , , 等 . . Algorithm 778: L-BFGS-B: Fortran subroutines for large-scale bound-constrained optimization . . ACM Trans Math Softw , , 1997 . . 23 ( ( 4 ): ): 550 - - 560 . . DOI: 10.1145/279232.279236 http://doi.org/10.1145/279232.279236 . .

CH Zou , , , E Yumer , , , JM Yang , , , 等 . . 3D-PRNN: generating shape primitives with recurrent neural networks . . IEEE Int Conf on Computer Vision , , 2017 . . p.900 - - 909 . . DOI: 10.1109/ICCV.2017.103 http://doi.org/10.1109/ICCV.2017.103 . .

Views

465

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

Recognition method for underwater communication signals that mimic dolphin whistles using phase-shifting modulation

Efficient privacy-preserving scheme for secure neural network inference

CRGT-SA: an interlaced and spatiotemporal deep learning model for network intrusion detection

Frequency-learning adversarial networks based on transfer learning for cross-scenario signal modulation classification

Ahybrid-model optimization algorithm based on the Gaussian process and particle swarm optimization for mixed-variable CNN hyperparameter automatic search

Related Author

Qingwang YAO

Jiajia JIANG

Xiaolong YU

Zhuochen LI

Fajie DUAN

Xiao FU

Xiaozong HOU

Yang MA

Related Institution

Shenyang Institute of Automation, Chinese Academy of Sciences

State Key Lab of Precision Measuring Technology and Instruments, Tianjin University

Purple Mountain Laboratories

School of Cyber Science and Engineering, Southeast University

School of Electronic and Electrical Engineering, Shanghai University of Engineering Science

Chat

Address：Zhejiang University Press, 148 Tianmushan Road, Hangzhou, China Postal code：310028
Tel：+86-571-88273162 Email：fitee@zju.edu.cn
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰