DOI QR코드

DOI QR Code

3D Point Cloud Enhancement based on Generative Adversarial Network

생성적 적대 신경망 기반 3차원 포인트 클라우드 향상 기법

  • Moon, HyungDo (Institute Of Applied Hologram, Wonkwang University) ;
  • Kang, Hoonjong (Department of Electronic Engineering, Wonkwang University) ;
  • Jo, Dongsik (School of IT Convergence, University of Ulsan)
  • Received : 2021.08.31
  • Accepted : 2021.09.15
  • Published : 2021.10.31

Abstract

Recently, point clouds are generated by capturing real space in 3D, and it is actively applied and serviced for performances, exhibitions, education, and training. These point cloud data require post-correction work to be used in virtual environments due to errors caused by the capture environment with sensors and cameras. In this paper, we propose an enhancement technique for 3D point cloud data by applying generative adversarial network(GAN). Thus, we performed an approach to regenerate point clouds as an input of GAN. Through our method presented in this paper, point clouds with a lot of noise is configured in the same shape as the real object and environment, enabling precise interaction with the reconstructed content.

Keywords

Acknowledgement

This work was supported by the Institute of Information & communications Technology Planning & Evaluation (IITP), grant funded by the Korean government(MSIT) (No. 2020-0-00226, Development of High-Definition, Unstructured Plenoptic video Acquisition Technology for Medium and Large Space).

References

  1. X. Zhang, G. Cheung, J. Pang, and D. Tian, "3D Point Cloud Enhancement Using Graph-Modelled multiview Depth Measurements," IEEE International Conference on Image Processing, pp. 3314-3318, 2020.
  2. K. S. Shin and S. Y. Shin "Real-time transmission of 3G point cloud data based on cGans," Journal of the Korea Society of Computer and Information, pp. 1482-1484, 2019.
  3. M. Wang, M. Ju, Y. Fan, S. Guo, M. Liao, H. Yang, D. He, and T. Komura, "3D Incomplete Point Cloud Surfaces Reconstruction With Segmentation and Feature-Enhancement," in IEEE Access, vol. 7, pp. 15272-15281, 2019. https://doi.org/10.1109/access.2019.2891959
  4. H. Li, Y. Zheng, X. Wu, and Q. Cai, "3D Model Generation and Reconstruction Using Conditional Generative Adversarial Network," International Journal of Computational Intelligence Systems, vol. 12, no. 2, pp. 697-705, 2019. https://doi.org/10.2991/ijcis.d.190617.001
  5. J. W. Kim, J. Y. Kim, H. S. Lim, and J. S. Kim, "Comparative Evaluation of 18F-FDG Brain PET/CT AI Images Obtained Using Generative Adversarial Network," The Korean Journal of Nuclear Medicine Technology, vol. 24, no. 1, pp. 15-19, 2020.
  6. D. K. Chung and I. P. Lee, "Point Cloud Classification Base On Deep Learning," Korea Society of Surveying, Geodesy, Photogrammetry, and Cartography, pp. 110-113, 2017.
  7. H. J. Lee, J. Y. Yun, J. W. Kim, and J. I. Park, "ICP based Point Cloud Contents Quality Improvement Method," The Korean Society Of Broad Engineer, pp. 200-201, 2020.
  8. J. G. Kim, J. H. Lee, S. M. Park, and K. H. Ko, "A Modified Method for Registration of 3D Point Clouds with a Low Overlap Ratio," Journal of the Korea Computer Graphics Society, vol. 24, no. 5, pp. 11-19, 2018. https://doi.org/10.15701/KCGS.2018.24.5.11
  9. X. Shi, J. Peng, J. Li, P. Yan, and H. Gong, "The Iterative Closest Point Registration Algorithm Based on the Normal Distribution Transformation," Computer Science, vol. 147, pp. 181-190, 2019.