A Comparative Review of AI-driven 3D Modelling for Simplified Photogrammetry and Object Acquisition

Year : 2024 | Volume : 11 | Issue : 02 | Page : 21 32
    By

    Surya Pratap,

  • Suhail Javed Quraishi,

  • Harsh Tekwani,

  • Ratnesh Chandra,

  1. Student, School of Computer Application, Manav Rachna International Institute of Research and Studies, Faridabad, Haryana, India
  2. Professor, School of Computer Application, Manav Rachna International Institute of Research and Studies, Faridabad, Haryana, India
  3. Student, School of Computer Application, Manav Rachna International Institute of Research and Studies, Faridabad, Haryana, India
  4. Student, School of Computer Application, Manav Rachna International Institute of Research and Studies, Faridabad, Haryana, India

Abstract

The field of photogrammetry, historically reliant on guide strategies, is undergoing a transformation with the emergence of AI-powered 3d modeling answers. This assessment work delves into this evolving panorama by using evaluating and comparing various AI-pushed gear presented by means of exclusive businesses. The study in particular makes a specialty of their effectiveness in simplifying photogrammetry workflows and facilitating the acquisition of 3D gadgets. The analysis contains a diverse range of tools, together with open-supply systems like NeRF through NVIDIA, Blender NeRF, LeRF, Open3D, and PyTorch3D. Additionally, the potential of the use of Generative antagonistic Networks (GANs) and other generative AI equipment for photogrammetry packages is explored. Through a complete examination of their functionalities, strengths, and barriers, the study gives treasured insights into the modern kingdom of AI-powered answers for photogrammetry. It also identifies key areas for destiny development and sheds light at the capability for AI to further revolutionize this vital era. This evaluates pursuits to function a valuable useful resource for researchers, practitioners, and absolutely everyone interested in understanding the effect of AI on photogrammetry and its capacity advantages for numerous programs.

Keywords: Photogrammetry, 3D modelling, NeRF, LeRF, Open3D, PyTorch3D, GAN, Generative AI

[This article belongs to Journal of Artificial Intelligence Research & Advances ]

How to cite this article:
Surya Pratap, Suhail Javed Quraishi, Harsh Tekwani, Ratnesh Chandra. A Comparative Review of AI-driven 3D Modelling for Simplified Photogrammetry and Object Acquisition. Journal of Artificial Intelligence Research & Advances. 2024; 11(02):21-32.
How to cite this URL:
Surya Pratap, Suhail Javed Quraishi, Harsh Tekwani, Ratnesh Chandra. A Comparative Review of AI-driven 3D Modelling for Simplified Photogrammetry and Object Acquisition. Journal of Artificial Intelligence Research & Advances. 2024; 11(02):21-32. Available from: https://journals.stmjournals.com/joaira/article=2024/view=155871


References

  1. Szeliski R. Computer vision: algorithms and applications. Cham: Springer Nature; 2022 Jan 3.
  2. Bello SA, Yu S, Wang C, Adam JM, Li J. Deep learning on 3D point clouds. Remote Sens. 2020 May 28; 12(11): 1729.
  3. Farshian A, Götz M, Cavallaro G, Debus C, Nießner M, Benediktsson JA, Streit A. Deep-Learning-Based 3-D Surface Reconstruction—A Survey. Proc IEEE. 2023 Oct 30; 111(11): 1464–1501.
  4. Horne R. 3D printing for dummies. John Wiley & Sons New Jersey, United States; 2023 Sep 5.
  5. Chen A, Xu Z, Zhao F, Zhang X, Xiang F, Yu J, Su H. Mvsnerf: Fast generalizable radiance field reconstruction from multi-view stereo. In Proceedings of the IEEE/CVF international conference on computer vision. 2021; 14124–14133.
  6. Dai A, Diller C, Nießner M. Sg-nn: Sparse generative neural networks for self-supervised scene completion of rgb-d scans. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020; 849–858.
  7. Zhang K, Riegler G, Snavely N, Koltun V. Nerf++: Analyzing and improving neural radiance fields. arXiv preprint arXiv:2010.07492. 2020 Oct 15.
  8. Barron JT, Mildenhall B, Tancik M, Hedman P, Martin-Brualla R, Srinivasan PP. Mip-nerf: A multiscale representation for anti-aliasing neural radiance fields. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021; 5855–5864.
  9. Kerr J, Kim CM, Goldberg K, Kanazawa A, Tancik M. Lerf: Language embedded radiance fields. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 2023; 19729–19739.
  10. Zhou QY, Park J, Koltun V. Open3D: A modern library for 3D data processing. arXiv preprint arXiv:1801.09847. 2018 Jan 30.
  11. Ravi N, Reizenstein J, Novotny D, Gordon T, Lo WY, Johnson J, Gkioxari G. Accelerating 3d deep learning with pytorch3d. arXiv preprint arXiv:2007.08501. 2020 Jul 16.
  12. Zhang J, Chen X, Cai Z, Pan L, Zhao H, Yi S, Yeo CK, Dai B, Loy CC. Unsupervised 3d shape completion through gan In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021; 1768–1777.
  13. Wang X, Ang MH, Lee GH. Point cloud completion by learning shape priors. In 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). 2020 Oct 24; 10719–10726.
  14. SENSING R. Photogrammetry and Remote Sensing. ISPRS Journal of Photogrammetry & Remote Sensing. 1998; 53(l7): 38.
  15. Sinha RK, Pandey R, Pattnaik R. Deep learning for computer vision tasks: a review. arXiv preprint arXiv:1804.03928. 2018 Apr 11.
  16. Mu F, Sifferman C, Jungerman S, Li Y, Han M, Gleicher M, Gupta M, Li Y. Towards 3D Vision with Low-Cost Single-Photon Cameras. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2024; 5302–5311.
Regular Issue Subscription Review Article
Volume 11
Issue 02
Received 24/05/2024
Accepted 23/06/2024
Published 10/07/2024
597

Login


My IP

PlumX Metrics