Application of Deep Learning to 3D Object Reconstruction From a Single Image

被引：0
|
作者：
Chen J. [1 ,2 ]
Zhang Y.-Q. [1 ]
Song P. [3 ]
Wei Y.-T. [1 ]
Wang Y. [4 ]
机构：
[1] School of Educational Information Technology, Central China Normal University, Wuhan
[2] Centre for Vision, Speech and Signal Processing, University of Surrey, Surrey
[3] Computer Graphics and Geometry Laboratory, École Polytechnique Fédérale de Lausanne, Lausanne
[4] Robotics Institute, The Hong Kong University of Science and Technology, Hong Kong
来源：
Zidonghua Xuebao/Acta Automatica Sinica | 2019年 / 45卷 / 04期
基金：
中国国家自然科学基金;
关键词：
3D reconstruction; Computer vision; Deep learning; Single image;
D O I：
10.16383/j.aas.2018.c180236
中图分类号：
学科分类号：
摘要：
3D object reconstruction from a single image is an important topic in computer vision, which has attracted enormous attention during the past decades. With the further study in deep learning, remarkable progress of 3D object reconstruction from a single image has been obtained in recent years. In this paper, we review the applications of deep learning models in the field of 3D object reconstruction from a single image. First, we introduce the research background and the current state-of-the-art of traditional methods. Then, we provide a brief overview of typical deep learning models and we describe the applications of deep learning techniques in 3D object reconstruction from a single image. After that, we list several commonly used data sets for 3D object reconstruction. Finally, we discuss current challenges and further research directions. Copyright © 2019 Acta Automatica Sinica. All rights reserved.
引用
收藏
页码：657 / 668
页数：11
相关论文
共 104 条
  • [1] Rezende D.J., Ali Eslami S.M., Mohamed S., Battaglia P., Jaderberg M., Heess N., Unsupervised learning of 3D structure from images, Proceedings of the 30th Conference on Neural Information Processing Systems (NIPS 2016), pp. 4996-5004, (2016)
  • [2] Haming K., Peters G., The structure-from-motion reconstruction pipeline-a survey with focus on short image sequences, Kybernetika, 46, 5, pp. 926-937, (2010)
  • [3] Lhuillier M., Quan L., A quasi-dense approach to surface reconstruction from uncalibrated images, IEEE Transactions on Pattern Analysis and Machine Intelligence, 27, 3, pp. 418-433, (2005)
  • [4] Habbecke M., Kobbelt L., A surface-growing approach to multi-view stereo reconstruction, Proceedings of the 2007 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8, (2007)
  • [5] Oswald M.R., Toppe E., Nieuwenhuis C., Cremers D., A review of geometry recovery from a single image focusing on curved object reconstruction, Innovations for Shape Analysis, pp. 343-378, (2013)
  • [6] Yi L., Shao L., Savva M., Huang H.B., Zhou Y., Wang Q.R., Et al., Large-scale 3D shape reconstruction and segmentation from ShapeNet Core55, (2017)
  • [7] Aspert N., Santa-Cruz D., Ebrahimi T., MESH: measuring errors between surfaces using the Hausdorff distance, Proceedings of the 2002 IEEE International Conference on Multimedia and Expo, pp. 705-708, (2002)
  • [8] Choy C.B., Xu D.F., Gwak J.Y., Chen K., Savarese S., 3D-R2N2: a unified approach for single and multi-view 3D object reconstruction, Proceedings of the 14th European Conference on Computer Vision, pp. 628-644, (2016)
  • [9] Fan H.Q., Su H., Guibas L., A point set generation network for 3D object reconstruction from a single image, Proceedings of the 2007 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2463-2471, (2017)
  • [10] Kemelmacher-Shlizerman I., Basri R., 3D face reconstruction from a single image using a single reference face shape, IEEE Transactions on Pattern Analysis and Machine Intelligence, 33, 2, pp. 394-405, (2011)
12345678910