Advertisement

A Comparative Study of 2D-to-3D Reconstruction Techniques

  • Surya PandeyEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 989)

Abstract

Image reconstruction is primarily an inverse problem, which directs the attention to reconstructing the original image from the given 2D image which may be blurred, consisting of some noise, and/or some damaged regions. The conversion to 3D involves finding out missing data. Rotation in conjunction with visualization from numerous perspectives of the image is facilitated by the third dimension for 3D reconstruction. Detailed and swift 3D reconstruction has established its applications in various fields such as Computer Vision, Medical Imaging, Virtual Reality, etc. The purpose of this paper is to bring attention to the thorough study of some state-of-the-art methods, which is used for fast 3D reconstruction. These methods include techniques, namely “Patch based Multi-View Stereo (PMVS), DAISY Descriptors, 3D point cloud, 3D Template matching, Recurrent Neural Network”. In the end, a comparative study of these methods based on various parameters is done to guide the readers to check the suitability of each approach.

Keywords

3D reconstruction Patch-based multi-View stereo DAISY descriptor 3D point cloud 3D template matching Recurrent neural network 

References

  1. 1.
    Furukawa, Yasutaka, Ponce, Jean: Accurate, dense, and robust multiview stereopsis. IEEE Trans. Pattern Anal. Mach. Intell. 32(8), 1362–1376 (2010)CrossRefGoogle Scholar
  2. 2.
    Wang, L., Chen, R., Kong, D.: An improved patch based multi-view stereo (PMVS) algorithm. In: 3rd International Conference on Computer Science and Service System. Atlantis Press (2014)Google Scholar
  3. 3.
    Ito, K., Xiong, K.: Gaussian filters for nonlinear filtering problems. IEEE Trans. Autom. Control. 45(5), 910–927 (2000)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Tola, E., Lepetit, V., Fua, P.: An efficient dense descriptor applied to wide-baseline stereo. IEEE Trans. Pattern Anal. Mach. Intell. 32(5), 815–830 (2010)CrossRefGoogle Scholar
  5. 5.
    Strecha, C., Fransens, R., Van Gool, L.: Combined depth and outlier estimation in multi-view stereo. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (2006)Google Scholar
  6. 6.
    Xue, B., et al.: A DAISY descriptor based multi-view stereo method for large-scale scenes. J. Vis. Commun. Image Represent. 35, 15–24 (2016)CrossRefGoogle Scholar
  7. 7.
    Shen, S.: Accurate multiple view 3D reconstruction using patch-based stereo for large-scale scenes. IEEE Trans. Image Process. 22(5), 1901–1914 (2013)Google Scholar
  8. 8.
    Kutulakos, K.N., Seitz, S.M.: A theory of shape by space carving. Int. J. Comput. Vis. 38(3), 199–218 (2000)Google Scholar
  9. 9.
    Shi, X., Zhao, B.: An algorithm for 3D reconstruction based on point-cloud image sequence. In: 2015 IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) (2015)Google Scholar
  10. 10.
    Haines, B., Bai, L.: Towards a robust patch based multi-view stereo technique for textureless and occluded 3D reconstruction. In: Computational Vision and Medical Image Processing V: Proceedings of the 5th Eccomas Thematic Conference on Computational Vision and Medical Image Processing (VipIMAGE 2015, Tenerife, Spain, 19–21 Oct 2015). CRC Press (2015)Google Scholar
  11. 11.
    Choy, C.B. et al.: 3d-r2n2: a unified approach for single and multi-view 3d object reconstruction. In: European Conference on Computer Vision. Springer International Publishing (2016)Google Scholar
  12. 12.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 1735–1780 (1997)CrossRefGoogle Scholar
  13. 13.
    Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. Advances in Neural Information Processing Systems (2014)Google Scholar
  14. 14.
    Liu, F., Shen, C., Lin, G.: Deep convolutional neural fields for depth estimation from a single image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)Google Scholar
  15. 15.
    Haines, B., Bai L.: Towards a robust patch based multi-view stereo technique for textureless and occluded 3D reconstruction. In: Computational Vision and Medical Image Processing V: Proceedings of the 5th Eccomas Thematic Conference on Computational Vision and Medical Image Processing (VipIMAGE 2015, Tenerife, Spain, 19–21 Oct 2015). CRC Press (2015)Google Scholar
  16. 16.
    Hammoudi, K. et al.: Generating occlusion-free textures for virtual 3D model of urban facades by fusing image and laser street data. In: 2012 IEEE Virtual Reality Workshops (VRW). IEEE (2012)Google Scholar
  17. 17.
    Fischer, J. et al.: A feature descriptor for texture-less object representation using 2D and 3D cues from RGB-D data. In: 2013 IEEE International Conference on Robotics and Automation (ICRA). IEEE (2013)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.Orchids The International SchoolSarjapur, BangaloreIndia

Personalised recommendations